© 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. 13129
    Prev
    Next
    INDEX
    Explanations

    numerical information about quantities related to events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant numerical data or statistics related to human casualties

    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
    orian
    -0.73
    cdn
    -0.71
     Practices
    -0.68
    thren
    -0.66
    ogie
    -0.63
    Artist
    -0.62
    '/
    -0.62
    ITH
    -0.60
    whatever
    -0.60
    ishers
    -0.60
    POSITIVE LOGITS
     ones
    0.80
    aband
    0.77
     aforementioned
    0.70
    apo
    0.66
     obligatory
    0.65
     prominently
    0.63
    enegger
    0.62
     infamous
    0.61
    oÄŁ
    0.60
     pione
    0.59
    Activations Density 0.287%

    No Known Activations