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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12868
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to various fields such as politics, analysis, and technology

    oai_token-act-pair · gpt-3.5-turbo

    entities and themes related to governance, politics, and social issues

    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
     Prosecut
    -0.65
     Infrastructure
    -0.60
     Strategic
    -0.55
     preventive
    -0.54
    lying
    -0.54
    mbudsman
    -0.53
     Administrative
    -0.53
     Spending
    -0.53
    Federal
    -0.53
     Doctrine
    -0.52
    POSITIVE LOGITS
     rave
    0.66
     somew
    0.60
    lehem
    0.59
    xual
    0.59
     smack
    0.57
     christ
    0.57
     Photographer
    0.55
    ĸļ
    0.55
     homage
    0.55
     mund
    0.54
    Activations Density 2.617%

    No Known Activations