© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 12781
    Prev
    Next
    INDEX
    Explanations

    statistical values and figures

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and percentages related to various groups or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assetsadobe
    -0.83
    prep
    -0.63
     bombard
    -0.62
     dx
    -0.60
     prep
    -0.59
    actionDate
    -0.59
     Purchase
    -0.58
     Esports
    -0.57
    lag
    -0.57
    eering
    -0.56
    POSITIVE LOGITS
    ½
    0.97
    %
    0.85
     percent
    0.82
     teasp
    0.80
     ½
    0.80
    thirds
    0.78
    thur
    0.76
    fort
    0.75
    retty
    0.75
    38
    0.73
    Activations Density 0.168%

    No Known Activations