© 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. 10-RES-JB
    11. 14076
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of football clubs and teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppo
    -0.96
    aminer
    -0.96
    onym
    -0.89
    enegger
    -0.86
    toggle
    -0.85
    cius
    -0.84
    ngth
    -0.80
    natureconservancy
    -0.80
    milo
    -0.78
    Ô
    -0.77
    POSITIVE LOGITS
     City
    1.32
    shire
    1.13
     Borough
    1.07
     Wolves
    1.06
     Wand
    1.06
     Middles
    1.04
     Palace
    1.03
     Athletic
    1.03
     Swansea
    1.01
     Tigers
    1.01
    Activations Density 0.067%

    No Known Activations