© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4149
    Prev
    Next
    INDEX
    Explanations

    universities and locations associated with news or events

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and proper names

    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
    •single token firings
    Individually fires on " Flint", " Clemson", " Catalonia", " JPMorgan", " BART", " Berkeley", " Watergate", ...

    No Comments

    Negative Logits
     Niet
    -0.71
    anwhile
    -0.53
    eatures
    -0.52
    ãĥ´
    -0.50
    awaru
    -0.49
    enegger
    -0.49
    76561
    -0.48
    herer
    -0.48
    ãĥĭ
    -0.47
     Seym
    -0.46
    POSITIVE LOGITS
    's
    0.62
    gard
    0.51
    weed
    0.46
    rock
    0.45
    omics
    0.44
    boro
    0.44
    ÃŃs
    0.43
    thal
    0.43
    fell
    0.43
     County
    0.41
    Activations Density 0.589%

    No Known Activations