© 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. 19310
    Prev
    Next
    INDEX
    Explanations

    mentions of sports games or results

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms and references to sports teams or franchises

    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
    osponsors
    -0.76
     Ples
    -0.73
    Trigger
    -0.70
    schild
    -0.69
    Senator
    -0.69
    paren
    -0.69
    Congress
    -0.69
    ording
    -0.69
    atel
    -0.68
    kie
    -0.68
    POSITIVE LOGITS
     midfield
    1.06
     offense
    1.03
     fanbase
    1.01
     preseason
    1.00
     playoff
    1.00
     own
    1.00
     offseason
    0.97
     defensive
    0.96
     roster
    0.94
     marquee
    0.93
    Activations Density 0.127%

    No Known Activations