Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2966
    Prev
    Next
    INDEX
    Explanations

    mentions of Republican party members or activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Republican Party

    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
    ortmund
    -0.78
    krit
    -0.78
    utils
    -0.74
    adr
    -0.73
    ensitive
    -0.69
    adobe
    -0.68
    variable
    -0.67
    iceps
    -0.67
    theless
    -0.66
    aminer
    -0.66
    POSITIVE LOGITS
     Party
    1.23
     presidential
    0.98
     nominee
    0.91
     majorities
    0.90
     gubernatorial
    0.86
     Majority
    0.85
     stronghold
    0.85
     frontrunner
    0.84
     politicians
    0.83
     strongh
    0.82
    Activations Density 0.053%

    No Known Activations