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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 7921
    Prev
    Next
    INDEX
    Explanations

    references to political identification categories, particularly "independents."

    oai_token-act-pair · gpt-3.5-turbo

    references to political affiliations, specifically independents and moderates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advertising
    -0.69
    ttp
    -0.69
    itual
    -0.67
     Sciences
    -0.64
    Detailed
    -0.64
    thur
    -0.63
    fare
    -0.63
    iton
    -0.63
     Liv
    -0.62
    NING
    -0.62
    POSITIVE LOGITS
     independents
    1.19
     strugg
    0.96
    ecided
    0.84
     centr
    0.73
     outsider
    0.73
     republic
    0.71
     overflow
    0.70
     peel
    0.69
    rats
    0.69
     minded
    0.68
    Activations Density 0.016%

    No Known Activations