© 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. 12088
    Prev
    Next
    INDEX
    Explanations

    language related to software or technical aspects

    oai_token-act-pair · gpt-3.5-turbo

    elements related to anticipation and future events

    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
    Newsletter
    -0.92
     ..."
    -0.81
    —"
    -0.79
     âĢ¦"
    -0.72
    ___
    -0.68
     ÂŃ
    -0.67
    laughter
    -0.62
     ''
    -0.62
     Photograph
    -0.62
    âĢ¢âĢ¢
    -0.61
    POSITIVE LOGITS
     utilizing
    1.18
     utilized
    1.13
     utilize
    1.06
     utilizes
    1.00
     rightfully
    0.97
     whilst
    0.95
    entimes
    0.94
     seemingly
    0.92
     unfortunately
    0.90
     Whilst
    0.90
    Activations Density 1.283%

    No Known Activations