© 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. 9971
    Prev
    Next
    INDEX
    Explanations

    references to the comic book character "Captain America"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character "Captain America."

    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
     exch
    -0.71
    ucl
    -0.70
    upon
    -0.67
    lé
    -0.65
    ittee
    -0.62
    raising
    -0.62
    entity
    -0.61
    continue
    -0.61
    âĶģ
    -0.60
    aternity
    -0.60
    POSITIVE LOGITS
    cy
    1.03
    cies
    0.96
     Kidd
    0.92
    bilt
    0.89
     Beef
    0.83
     Crunch
    0.83
     Picard
    0.82
     America
    0.80
     Nem
    0.80
     Toad
    0.79
    Activations Density 0.050%

    No Known Activations