© 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. 2-RES-JB
    11. 12948
    Prev
    Next
    INDEX
    Explanations

    activities related to American football, particularly catching and playing different positions

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to football players and their positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHIP
    -0.91
    theless
    -0.77
    lag
    -0.75
     CET
    -0.74
    microsoft
    -0.72
    uckland
    -0.72
    staking
    -0.71
    sonian
    -0.71
    hend
    -0.70
    Austral
    -0.69
    POSITIVE LOGITS
     rookie
    1.11
     linebacker
    1.02
     cornerback
    0.98
     linebackers
    0.96
     rookies
    0.95
     quarterback
    0.94
     undrafted
    0.91
     rosters
    0.90
     Rookie
    0.89
     freshman
    0.87
    Activations Density 0.504%

    No Known Activations