© 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. 14039
    Prev
    Next
    INDEX
    Explanations

    names of sports players

    oai_token-act-pair · gpt-3.5-turbo

    references to sports team player rosters and related changes

    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
    renheit
    -0.77
     nonviolent
    -0.76
     peacefully
    -0.71
    realDonaldTrump
    -0.71
     millennia
    -0.70
    externalActionCode
    -0.70
    Consumer
    -0.70
    consumer
    -0.69
     Fahrenheit
    -0.69
     polluted
    -0.68
    POSITIVE LOGITS
     signings
    1.60
     roster
    1.44
     rosters
    1.37
     additions
    1.35
     replacements
    1.25
     squad
    1.23
     rookies
    1.22
     departures
    1.21
     lineup
    1.21
     squads
    1.17
    Activations Density 0.650%

    No Known Activations