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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 7043
    Prev
    Next
    INDEX
    Explanations

    mentions of political affiliations, specifically the word "Democrat"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Democratic Party

    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
    icles
    -0.79
    obar
    -0.77
    obyl
    -0.74
     Jehovah
    -0.74
    istic
    -0.73
    obo
    -0.67
    ordon
    -0.66
    ctica
    -0.66
    rawdownloadcloneembedreportprint
    -0.65
    renheit
    -0.65
    POSITIVE LOGITS
     Party
    0.95
    INTON
    0.77
     nominate
    0.76
     caucuses
    0.76
    paces
    0.75
     caucus
    0.74
     nominee
    0.74
     strongh
    0.73
     stronghold
    0.73
     frontrunner
    0.71
    Activations Density 0.045%

    No Known Activations