© 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. 14128
    Prev
    Next
    INDEX
    Explanations

    names of people or entities involved in legal or political matters

    oai_token-act-pair · gpt-3.5-turbo

    subjects or entities listed in a sequence

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Decre
    -0.74
    planes
    -0.70
    process
    -0.63
     heights
    -0.62
    Results
    -0.60
     feast
    -0.59
    FIX
    -0.58
     ponies
    -0.57
     trunc
    -0.57
    ");
    -0.57
    POSITIVE LOGITS
     Jr
    1.05
     Sr
    1.00
     chairman
    0.94
     director
    0.91
     dean
    0.90
     spokesman
    0.90
     founder
    0.88
     QC
    0.86
     PhD
    0.85
     aka
    0.85
    Activations Density 0.124%

    No Known Activations