© 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. 12880
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals with initials followed by numbers or periods

    oai_token-act-pair · gpt-3.5-turbo

    periods in text

    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
    enegger
    -0.72
    SourceFile
    -0.68
    anmar
    -0.66
    ģĸ
    -0.61
     sanct
    -0.61
    saf
    -0.60
    cient
    -0.59
    chwitz
    -0.59
    emort
    -0.59
    ahime
    -0.58
    POSITIVE LOGITS
     Boone
    0.81
    rex
    0.79
    Rex
    0.78
     Rowe
    0.77
     Eliot
    0.75
    shirts
    0.72
     Davies
    0.71
    shirt
    0.67
    GY
    0.63
    Ds
    0.63
    Activations Density 0.025%

    No Known Activations