© 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. 12294
    Prev
    Next
    INDEX
    Explanations

    mentions of the celebrity "Lady Gaga"

    oai_token-act-pair · gpt-3.5-turbo

    references to Lady Gaga

    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
    ozy
    -0.90
    ypes
    -0.83
    venants
    -0.76
    osed
    -0.76
    osta
    -0.72
    ython
    -0.72
    aq
    -0.71
    ideo
    -0.71
    ographed
    -0.70
    eger
    -0.69
    POSITIVE LOGITS
     Gaga
    1.55
    bug
    1.22
    maid
    1.17
    bugs
    1.09
    bird
    1.06
    woman
    1.04
    killers
    0.99
     Madonna
    0.96
    killer
    0.96
    wives
    0.94
    Activations Density 0.069%

    No Known Activations