© 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. 13212
    Prev
    Next
    INDEX
    Explanations

    occurrences of "or" in the text and emphasize possibilities or choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest possibilities or uncertainties

    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
     Pony
    -0.83
     Cth
    -0.76
     Civilization
    -0.61
     Steel
    -0.60
    estro
    -0.58
     pandemonium
    -0.57
     mummy
    -0.57
     Values
    -0.57
    "}],"
    -0.57
     Pieces
    -0.56
    POSITIVE LOGITS
    acles
    1.23
    chard
    1.17
    acular
    1.05
    acle
    1.04
    chid
    1.01
    leans
    0.95
    gin
    0.93
    nery
    0.92
    lov
    0.90
     implied
    0.89
    Activations Density 0.088%

    No Known Activations