© 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. 18665
    Prev
    Next
    INDEX
    Explanations

    mentions of football games and players

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sporting events and games

    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
     Pengu
    -0.81
    rylic
    -0.80
    govtrack
    -0.74
     Pradesh
    -0.74
     UNCLASSIFIED
    -0.73
    ku
    -0.72
    olas
    -0.71
    ugu
    -0.70
    enza
    -0.70
     QC
    -0.70
    POSITIVE LOGITS
     NFC
    1.63
     Steelers
    1.61
     Colts
    1.60
     Broncos
    1.59
     Seahawks
    1.58
     Packers
    1.58
     NFL
    1.56
     Redskins
    1.55
     Bengals
    1.54
     Ravens
    1.52
    Activations Density 0.959%

    No Known Activations