© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11326
    Prev
    Next
    INDEX
    Explanations

    baseball statistics and game outcomes

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to sports performance and scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.66
     thous
    -0.60
     accompanying
    -0.60
     thousands
    -0.60
     Rupert
    -0.59
     Rend
    -0.59
     Valent
    -0.58
     swearing
    -0.58
     multiplying
    -0.57
    staking
    -0.56
    POSITIVE LOGITS
    QB
    0.93
    ½
    0.92
    nd
    0.85
    ND
    0.80
    GG
    0.79
    FB
    0.76
     ½
    0.76
    OT
    0.76
    rd
    0.73
    PO
    0.72
    Activations Density 0.114%

    No Known Activations