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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20253
    Prev
    Next
    INDEX
    Explanations

    references to legislative bodies or specific political activities

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative bodies or institutions

    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
    ãĥ¼ãĥĨ
    -0.77
    iously
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
    ashtra
    -0.68
     tsun
    -0.67
    =-=-=-=-=-=-=-=-
    -0.66
    ibly
    -0.66
    ilitary
    -0.66
    amount
    -0.64
    ãĤ¶
    -0.64
    POSITIVE LOGITS
     Representatives
    1.21
     Commons
    0.96
     senators
    0.87
     Lords
    0.83
     Parliament
    0.80
     Senators
    0.79
     Assembly
    0.78
     Cards
    0.78
     Reps
    0.78
     governors
    0.75
    Activations Density 0.033%

    No Known Activations