© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12171
    Prev
    Next
    INDEX
    Explanations

    words related to politics

    oai_token-act-pair · gpt-3.5-turbo

    references to political themes and concepts

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

    No Comments

    Negative Logits
     Cancel
    -0.86
    enment
    -0.86
    actory
    -0.84
    wered
    -0.83
    ered
    -0.82
    olen
    -0.80
    eret
    -0.79
    xt
    -0.78
    ibles
    -0.77
     Carbuncle
    -0.77
    POSITIVE LOGITS
     correctness
    1.31
     affili
    1.02
     affiliation
    1.00
     campaigns
    0.91
     activism
    0.89
     clout
    0.89
     partisans
    0.87
     campaigning
    0.86
     rhetoric
    0.86
     affairs
    0.84
    Activations Density 0.035%

    No Known Activations