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. 10-RES-JB
    6. 15887
    Prev
    Next
    INDEX
    Explanations

    mentions of political parties, campaign financing, and political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political parties and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alys
    -1.01
     realised
    -0.96
     realise
    -0.90
     analyse
    -0.86
     onwards
    -0.85
    isations
    -0.85
     civilisation
    -0.84
     fulfil
    -0.84
     analysed
    -0.78
     fuelled
    -0.78
    POSITIVE LOGITS
     gubernatorial
    1.55
     Congressman
    1.49
     Libertarian
    1.47
     RNC
    1.41
     GOP
    1.41
     Republican
    1.40
     lobbyist
    1.38
     congressman
    1.36
     Iowa
    1.35
     Democrat
    1.33
    Activations Density 0.915%

    No Known Activations