© 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. 14111
    Prev
    Next
    INDEX
    Explanations

    large numerical figures in texts

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable statistics or numbers related to human casualties or demographics

    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
    itiz
    -0.76
    ĸļ
    -0.69
     envy
    -0.65
     Dating
    -0.63
    urer
    -0.63
    artisan
    -0.63
    agall
    -0.62
    imen
    -0.62
    ourage
    -0.61
    odox
    -0.61
    POSITIVE LOGITS
     hectares
    1.11
     acres
    1.03
     sq
    0.99
     tonnes
    0.91
     pounds
    0.90
     gallons
    0.90
    lb
    0.90
     square
    0.89
     lbs
    0.89
    +
    0.87
    Activations Density 0.081%

    No Known Activations