© 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. 4-RES-JB
    11. 7529
    Prev
    Next
    INDEX
    Explanations

    locations related to political events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations or landmarks

    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
    raft
    -0.92
     betting
    -0.75
     runaway
    -0.74
     gambling
    -0.71
    erm
    -0.67
    blown
    -0.66
     withdrawals
    -0.65
     substance
    -0.65
    states
    -0.65
    orem
    -0.64
    POSITIVE LOGITS
    rir
    0.91
     Square
    0.88
     Aven
    0.76
    ãĥĭ
    0.75
    rio
    0.72
    thouse
    0.70
    rence
    0.69
    vard
    0.69
    itbart
    0.69
     Beir
    0.68
    Activations Density 0.021%

    No Known Activations