© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 8153
    Prev
    Next
    INDEX
    Explanations

    references to people in a specific group that the document's author is part of

    oai_token-act-pair · gpt-3.5-turbo

    references to peers and contemporaries in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    rament
    -0.69
    ruction
    -0.68
    Jew
    -0.60
     Werewolf
    -0.60
    trap
    -0.59
     TRUMP
    -0.59
     Salvation
    -0.59
     Arena
    -0.59
     Sold
    -0.58
    lot
    -0.58
    POSITIVE LOGITS
     peers
    4.21
     peer
    2.10
     contemporaries
    2.04
     classmates
    1.96
     counterparts
    1.81
     colleagues
    1.77
     brethren
    1.58
    peer
    1.49
     superiors
    1.48
     mentors
    1.48
    Activations Density 0.009%

    No Known Activations