© 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. 21220
    Prev
    Next
    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    prominent individuals and their activities or affiliations

    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
     thereafter
    -0.80
     afterward
    -0.78
    }.
    -0.70
     afterwards
    -0.69
     [*
    -0.65
    .).
    -0.64
    )."
    -0.63
     beforehand
    -0.61
     UNCLASSIFIED
    -0.61
    )).
    -0.60
    POSITIVE LOGITS
    reetings
    0.70
     Brewing
    0.70
    Arcade
    0.68
    Coin
    0.66
    ratom
    0.64
    Wiki
    0.64
     Calculator
    0.63
    isoft
    0.62
    Wallet
    0.61
     Album
    0.61
    Activations Density 0.895%

    No Known Activations