© 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
    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. 4020
    Prev
    Next
    INDEX
    Explanations

    mentions of sports results or competitive events ending in a draw

    oai_token-act-pair · gpt-3.5-turbo

    references to matches that ended in a draw

    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
    nown
    -0.95
    userc
    -0.82
    illon
    -0.81
    ambers
    -0.76
    anamo
    -0.76
    cffffcc
    -0.75
     srf
    -0.75
     bom
    -0.73
    icone
    -0.71
    ternity
    -0.71
    POSITIVE LOGITS
    card
    0.94
    cards
    0.89
     Draw
    0.88
    draw
    0.87
    strings
    0.82
     draw
    0.81
    backs
    0.79
    downs
    0.78
    lings
    0.76
    string
    0.73
    Activations Density 0.009%

    No Known Activations