© 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. 4-RES-JB
    11. 8614
    Prev
    Next
    INDEX
    Explanations

    positions in American football, specifically cornerback and safety

    oai_token-act-pair · gpt-3.5-turbo

    terms related to defensive positions in football

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

    No Comments

    Negative Logits
    izoph
    -0.75
    itarian
    -0.68
     favour
    -0.68
     Orwell
    -0.67
     autonomous
    -0.67
    ombat
    -0.67
     drinking
    -0.66
    arist
    -0.66
    ighty
    -0.64
    sth
    -0.64
    POSITIVE LOGITS
     linebacker
    0.83
     cornerback
    0.82
     waivers
    0.78
     Bryce
    0.77
    backs
    0.76
    olor
    0.73
     =================
    0.72
     Franch
    0.71
     linebackers
    0.71
     Trey
    0.70
    Activations Density 0.026%

    No Known Activations