© 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. 7-RES-JB
    11. 11220
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events that may involve conflict, decision-making, or significant consequences

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to conflict, legal matters, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ª
    -0.63
    Tes
    -0.63
    MAX
    -0.62
    ãĥ¼ãĥĨ
    -0.60
    ¯
    -0.60
    uador
    -0.60
     Citiz
    -0.60
     teens
    -0.58
    Te
    -0.57
    °
    -0.57
    POSITIVE LOGITS
    .
    0.91
    .;
    0.86
    .:
    0.85
    .,
    0.84
    .#
    0.82
    .$
    0.82
    .(
    0.81
    .?
    0.78
    ;
    0.77
    .–
    0.75
    Activations Density 0.641%

    No Known Activations