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

    Neuronpedia

    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. 11-RES-JB
    11. 24416
    Prev
    Next
    INDEX
    Explanations

    key political terms and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and military terminology

    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
    enegger
    -0.73
    eers
    -0.73
    hyde
    -0.69
    smith
    -0.68
    ĸļ
    -0.65
    tics
    -0.64
     crim
    -0.61
     Cardinal
    -0.61
    inelli
    -0.61
     Cov
    -0.61
    POSITIVE LOGITS
    asp
    0.77
     missile
    0.70
     nuclear
    0.67
    insk
    0.64
     airst
    0.63
     uranium
    0.63
    adr
    0.62
    SSL
    0.62
    utonium
    0.61
    Asia
    0.61
    Activations Density 0.253%

    No Known Activations