© 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. 8-RES-JB
    11. 17104
    Prev
    Next
    INDEX
    Explanations

    references to individuals named "Gill"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Gill."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.64
     ãĤµ
    -0.64
    ension
    -0.62
     Sorceress
    -0.58
     semin
    -0.57
     cytok
    -0.57
     compr
    -0.57
     sight
    -0.57
    BOOK
    -0.56
     malfunction
    -0.56
    POSITIVE LOGITS
    igan
    1.27
    iard
    1.24
    iland
    1.22
    espie
    1.11
    igans
    1.09
    iants
    1.07
    iage
    1.07
    ibr
    1.02
    iam
    0.97
    wyn
    0.95
    Activations Density 0.028%

    No Known Activations