© 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 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. 8-RES-JB
    11. 4176
    Prev
    Next
    INDEX
    Explanations

    words related to personal or societal actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to "actions" and their implications or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bid
    -0.89
    anus
    -0.75
    ļéĨĴ
    -0.70
    skinned
    -0.69
    vu
    -0.65
    weights
    -0.63
     Dwell
    -0.63
     comma
    -0.62
    ickets
    -0.61
    inately
    -0.61
    POSITIVE LOGITS
    uate
    1.01
    ives
    0.94
     actions
    0.92
    terday
    0.91
    uits
    0.90
    hops
    0.88
    uations
    0.87
     undertaken
    0.86
    ivism
    0.86
     ACTIONS
    0.86
    Activations Density 0.060%

    No Known Activations