© 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. 14122
    Prev
    Next
    INDEX
    Explanations

    descriptions of sizes, weights, and measures

    oai_token-act-pair · gpt-3.5-turbo

    numerical measurements and specifications

    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
     proactive
    -0.83
     scapego
    -0.79
     Cosponsors
    -0.73
    happy
    -0.71
    rompt
    -0.69
     nos
    -0.67
    elist
    -0.67
    pkg
    -0.67
    ª
    -0.66
     exclus
    -0.66
    POSITIVE LOGITS
     weighs
    1.16
     diameter
    1.14
     tallest
    1.10
     thickness
    0.96
    iameter
    0.96
     heaviest
    0.95
     curv
    0.94
     circumference
    0.91
     dwarf
    0.90
     dens
    0.90
    Activations Density 0.846%

    No Known Activations