© 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. 11135
    Prev
    Next
    INDEX
    Explanations

    names of sports teams or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations or sports 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
    schild
    -1.08
    enegger
    -1.01
    umenthal
    -0.86
    olkien
    -0.85
    bnb
    -0.80
    alore
    -0.79
    byn
    -0.76
    Ô
    -0.73
    chwitz
    -0.73
    EVA
    -0.71
    POSITIVE LOGITS
     Eagles
    1.14
     Buccaneers
    1.09
     Royals
    1.07
     Falcons
    1.07
     Wolves
    1.06
     Bulldogs
    1.05
     Chiefs
    1.04
     Bears
    1.01
     Lions
    1.00
     Panthers
    1.00
    Activations Density 0.093%

    No Known Activations