© 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. 7-RES-JB
    11. 14129
    Prev
    Next
    INDEX
    Explanations

    sports-related terms, particularly those related to achievements and awards like "Olympic" and "All-Star."

    oai_token-act-pair · gpt-3.5-turbo

    references to Olympic participation or achievements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    haar
    -0.78
    ilst
    -0.75
    asty
    -0.74
     Teams
    -0.72
    amera
    -0.71
    het
    -0.70
    rative
    -0.68
    alan
    -0.67
    asket
    -0.66
    hops
    -0.66
    POSITIVE LOGITS
     reigning
    0.87
     Emmy
    0.75
     novelist
    0.73
     Bucc
    0.73
     traveler
    0.71
     veteran
    0.70
     traveller
    0.70
     collaborator
    0.70
     resident
    0.69
     adherent
    0.66
    Activations Density 0.036%

    No Known Activations