© 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. 9-RES-JB
    11. 10244
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize exclusivity or limitation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    »Ĵ
    -0.93
    EStream
    -0.68
    ³
    -0.67
    etc
    -0.66
    ĸ
    -0.65
    UGE
    -0.62
    ij士
    -0.61
    glomer
    -0.61
    Various
    -0.60
    nect
    -0.60
    POSITIVE LOGITS
    oped
    0.75
     physically
    0.69
    tem
    0.65
    schild
    0.63
    ional
    0.63
     survive
    0.62
     obe
    0.61
    ifiable
    0.60
     visually
    0.59
     financially
    0.58
    Activations Density 0.038%

    No Known Activations