© 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. 12796
    Prev
    Next
    INDEX
    Explanations

    numeric values related to quantities or percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly percentages and monetary figures

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.87
     Correspond
    -0.65
    ↵Âł
    -0.65
     fame
    -0.63
     Tiff
    -0.61
     everywhere
    -0.59
     Participant
    -0.58
    bard
    -0.58
    Meta
    -0.57
    TextColor
    -0.57
    POSITIVE LOGITS
     percent
    0.96
     cents
    0.96
    %"
    0.95
     million
    0.91
     acres
    0.89
     months
    0.87
     pounds
    0.86
     euros
    0.85
    %
    0.84
     billion
    0.84
    Activations Density 0.254%

    No Known Activations