© 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. 12812
    Prev
    Next
    INDEX
    Explanations

    topics or events of interest that are recommended to be watched or paid attention to

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to critical current events or issues

    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
    Relations
    -0.79
    icy
    -0.73
    auld
    -0.70
    acements
    -0.69
     mascul
    -0.67
    hyp
    -0.67
    hower
    -0.67
    namese
    -0.65
    zinski
    -0.65
    sheet
    -0.65
    POSITIVE LOGITS
    EStream
    0.84
    }
    0.79
     â
    0.77
     sec
    0.76
     ff
    0.74
     Terra
    0.72
     Hert
    0.72
     Snapdragon
    0.72
    .}
    0.71
     FF
    0.71
    Activations Density 0.215%

    No Known Activations