© 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. 12-RES-JB
    11. 4786
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and political issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases and terms related to legal, political, and social accountability issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     pictured
    -0.63
     scanned
    -0.62
    agine
    -0.62
     closest
    -0.58
     Dustin
    -0.57
     OG
    -0.56
     Aurora
    -0.56
     groom
    -0.55
     Compass
    -0.55
     released
    -0.55
    POSITIVE LOGITS
    entious
    0.95
    acious
    0.93
    itudes
    0.91
    itious
    0.86
    igious
    0.84
    imony
    0.84
    leness
    0.83
    uitous
    0.82
    itations
    0.82
    atism
    0.81
    Activations Density 0.358%

    No Known Activations