Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14059
    Prev
    Next
    INDEX
    Explanations

    organizations or associations related to manufacturing

    oai_token-act-pair · gpt-3.5-turbo

    words related to manufacturers and their associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The suffix "-ers" attached to nouns, frequently denoting a group of people or things performing a similar action or profession (e.g., manufacturers, lecturers, insurers). There are also instances of "-er" suffixes attached to nouns modifying the base noun (e.g., torturer, perjurer).

    eleuther_acts_top20 · gemini-1.5-flashTriggered by @johnny

    Suffixes include "urers", "urer", "ers", or "ious" are found at the end of words. "Urers" and "urer" designate a job function. "Ious" indicates a strong emotional state.

    eleuther_acts_top20 · gemini-2.0-flashTriggered by @johnny
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HQ
    -0.64
     Jump
    -0.62
     headquarters
    -0.60
     Halo
    -0.59
     chili
    -0.59
     rh
    -0.57
     po
    -0.56
     music
    -0.56
     overtime
    -0.56
     Cop
    -0.56
    POSITIVE LOGITS
    urers
    4.73
    urer
    3.60
    ured
    2.08
    uring
    2.06
    ures
    2.05
    urance
    1.99
    ure
    1.77
    urances
    1.54
    URES
    1.51
    ury
    1.47
    Activations Density 0.009%

    No Known Activations