© 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. 11-RES-JB
    11. 12915
    Prev
    Next
    INDEX
    Explanations

    mentions of personal accomplishments and progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to competitive sports and fighter performance

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Archae
    -0.88
    Tesla
    -0.88
     ASD
    -0.86
    Apple
    -0.83
    Minecraft
    -0.82
    artifacts
    -0.82
     settlers
    -0.78
    ulhu
    -0.77
     VW
    -0.77
     obs
    -0.76
    POSITIVE LOGITS
    UFC
    1.95
     UFC
    1.90
     MMA
    1.89
     fighters
    1.61
     boxing
    1.55
     Mayweather
    1.53
     fighter
    1.48
     Rouse
    1.46
    fight
    1.44
     fights
    1.44
    Activations Density 0.527%

    No Known Activations