© 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 EvalsExportsinterp-engineNEWAPI 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. 21190
    Prev
    Next
    INDEX
    Explanations

    words related to locations and actions happening in various places

    oai_token-act-pair · gpt-3.5-turbo

    references to notable people, events, and actions within a societal context

    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
    buquerque
    -0.73
    prus
    -0.68
    ILA
    -0.67
    iami
    -0.64
    ï¸ı
    -0.60
     CBI
    -0.60
    esa
    -0.58
    stanbul
    -0.57
     Quebec
    -0.57
    ulhu
    -0.57
    POSITIVE LOGITS
    .[
    0.91
    .
    0.88
    .(
    0.80
    .–
    0.78
     nightly
    0.73
    ,.
    0.73
    ãĢĤ
    0.72
     ().
    0.72
    .$
    0.72
    .<
    0.69
    Activations Density 0.483%

    No Known Activations