© 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. 11431
    Prev
    Next
    INDEX
    Explanations

    copyright and legal information at the end of text

    oai_token-act-pair · gpt-3.5-turbo

    copyright and legal information

    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
     deduct
    -0.71
     displ
    -0.64
    heet
    -0.62
     churn
    -0.61
    pace
    -0.61
    lets
    -0.61
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.59
     fortunes
    -0.59
    let
    -0.59
     shifts
    -0.55
    POSITIVE LOGITS
    _-
    1.29
    webkit
    1.15
    =-=-=-=-=-=-=-=-
    1.01
    \-
    0.91
    =-=-
    0.89
    /-
    0.83
    =-=-=-=-
    0.80
     [|
    0.78
    ?????-
    0.77
    icious
    0.74
    Activations Density 0.037%

    No Known Activations