© 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. 9-RES-JB
    11. 1014
    Prev
    Next
    INDEX
    Explanations

    references to historical figures or locations, particularly related to Woodrow Wilson

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Woodrow Wilson" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.84
    advertisement
    -0.81
    incial
    -0.81
    orius
    -0.78
    rencies
    -0.77
    Äĩ
    -0.76
    fecture
    -0.73
    replace
    -0.70
    nesota
    -0.68
    merga
    -0.68
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.82
     lett
    0.73
     è£ıè
    0.69
    ADRA
    0.68
    zona
    0.65
     Chapters
    0.63
     Books
    0.61
     Roberts
    0.60
    Oracle
    0.59
    Gray
    0.59
    Activations Density 0.270%

    No Known Activations