© 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. 12-RES-JB
    11. 2421
    Prev
    Next
    INDEX
    Explanations

    statistics and social issues related to different demographic groups

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    statistical data and percentages related to social issues and demographics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     beh
    -0.55
    hum
    -0.55
    unity
    -0.53
    along
    -0.51
     afar
    -0.51
    bye
    -0.50
     reckoning
    -0.50
     yours
    -0.48
    angle
    -0.48
     theirs
    -0.47
    POSITIVE LOGITS
     percent
    1.20
    %
    1.16
    pc
    0.93
     Percent
    0.90
    %-
    0.88
    percent
    0.84
    %"
    0.82
    %,
    0.77
     million
    0.77
    %)
    0.77
    Activations Density 0.128%

    No Known Activations