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. 2-RES-JB
    6. 20580
    Prev
    Next
    INDEX
    Explanations

    words related to smartphones

    oai_token-act-pair · gpt-3.5-turbo

    words related to the term "ph" (likely indicating a focus on phrases that include "ph")

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -1.09
    ndra
    -0.79
    HCR
    -0.78
    uyomi
    -0.67
    PRES
    -0.67
     merit
    -0.66
    ACTED
    -0.65
    ãĤ¤ãĥĪ
    -0.64
    Issue
    -0.61
     Recovery
    -0.61
    POSITIVE LOGITS
    oenix
    1.16
    araoh
    1.09
    izoph
    1.08
    antom
    1.05
    obia
    1.02
    osph
    1.01
    yll
    0.98
    ilipp
    0.96
    ysics
    0.95
    oton
    0.94
    Activations Density 0.012%

    No Known Activations