© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 23712
    Prev
    Next
    INDEX
    Explanations

    scores of sports games

    oai_token-act-pair · gpt-3.5-turbo

    scores and statistics related to sports matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tabl
    -0.60
    enegger
    -0.59
     descriptions
    -0.59
     swearing
    -0.58
    awaru
    -0.57
     euphem
    -0.56
     obe
    -0.56
     totem
    -0.55
     Mara
    -0.55
     periodic
    -0.54
    POSITIVE LOGITS
    vs
    1.11
    v
    0.91
    OT
    0.80
    -
    0.79
    ½
    0.78
    GG
    0.78
    Vs
    0.77
    LCS
    0.77
     ½
    0.76
    ND
    0.76
    Activations Density 0.045%

    No Known Activations