© 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. 1-RES-JB
    11. 14275
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and people's names, especially with special characters mixed in

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative actions or significant legal decisions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     exha
    -0.57
    Ĥİ
    -0.55
     carbohyd
    -0.52
     Pastebin
    -0.51
     referen
    -0.51
     tremend
    -0.51
    catentry
    -0.50
    ccording
    -0.50
     pse
    -0.48
    wcs
    -0.47
    POSITIVE LOGITS
    ensis
    0.58
    imore
    0.55
    orf
    0.54
    ragon
    0.54
    ite
    0.52
    atics
    0.51
    u
    0.50
    bis
    0.50
    iland
    0.49
    ierre
    0.49
    Activations Density 2.243%

    No Known Activations