© 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. 3340
    Prev
    Next
    INDEX
    Explanations

    information or statements related to official communications like press releases and news reports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to press releases and media communications

    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
     stadiums
    -0.75
     Poles
    -0.74
     trusts
    -0.74
     ceilings
    -0.74
     Legions
    -0.71
     belts
    -0.69
     motorcycles
    -0.68
     exits
    -0.67
     airplanes
    -0.67
     Colleges
    -0.67
    POSITIVE LOGITS
     pamphlet
    1.24
     article
    1.19
    catentry
    1.13
     snippet
    1.08
     booklet
    1.08
     summary
    1.07
    vertisement
    1.07
     infographic
    1.05
    isode
    1.05
     bulletin
    1.05
    Activations Density 0.279%

    No Known Activations