© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 16934
    Prev
    Next
    INDEX
    Explanations

    mentions of modifications or mods in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to modifications (mods) in gaming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸
    -0.73
    lihood
    -0.72
     Bucc
    -0.71
     Baptist
    -0.71
     Situation
    -0.71
     Winds
    -0.70
     Unic
    -0.70
     Parish
    -0.70
     Apost
    -0.68
     Lauder
    -0.68
    POSITIVE LOGITS
    icum
    1.28
    ding
    1.12
    elled
    1.11
    ifiable
    1.08
    ded
    0.95
    ifies
    0.93
    ulo
    0.93
    ifications
    0.93
    der
    0.89
    aton
    0.85
    Activations Density 0.006%

    No Known Activations