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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 18055
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "Hurry"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Hur" and its variations in the context of various subjects, particularly in relation to specific people or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skydragon
    -0.72
     Bastard
    -0.63
     Gleaming
    -0.63
     Babel
    -0.62
    volent
    -0.61
    Constructed
    -0.60
    ç¥ŀ
    -0.60
    ographically
    -0.59
    OTE
    -0.58
     settlements
    -0.58
    POSITIVE LOGITS
    ricane
    1.35
    ricanes
    1.25
    witz
    1.23
    rican
    1.22
    rah
    1.16
    acan
    1.10
    ley
    1.04
    rying
    1.00
    ried
    0.97
    ries
    0.96
    Activations Density 0.034%

    No Known Activations