© 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. 2-RES-JB
    11. 12064
    Prev
    Next
    INDEX
    Explanations

    references to political constituents

    oai_token-act-pair · gpt-3.5-turbo

    references to constituents, typically in a political or community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.82
    laus
    -0.81
    OUT
    -0.77
    cer
    -0.72
    orne
    -0.69
    Pont
    -0.69
    immer
    -0.68
    imb
    -0.68
    oon
    -0.66
    use
    -0.66
    POSITIVE LOGITS
     constituents
    1.42
     constituent
    1.10
     constituencies
    0.86
    é¾įå¥ij士
    0.86
    arians
    0.79
    iants
    0.78
    iband
    0.77
    mate
    0.76
     donors
    0.73
    members
    0.71
    Activations Density 0.002%

    No Known Activations