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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 3866
    Prev
    Next
    INDEX
    Explanations

    instances of the word "draw" in various contexts, such as sports outcomes, results, or artistic representations

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive outcomes that result in a tie or draw

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ican
    -0.83
    onte
    -0.76
    icone
    -0.74
     bom
    -0.71
    nown
    -0.70
    phia
    -0.68
    ĨĴ
    -0.67
    Ħ¢
    -0.67
    ĺħ
    -0.66
    userc
    -0.66
    POSITIVE LOGITS
    cards
    1.10
    card
    1.09
    downs
    0.95
    down
    0.93
    friend
    0.83
     Draw
    0.81
    board
    0.81
    strings
    0.80
    backs
    0.80
    Card
    0.79
    Activations Density 0.018%

    No Known Activations