© 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. 9-RES-JB
    11. 10356
    Prev
    Next
    INDEX
    Explanations

    references to cycling events like the Tour de France

    oai_token-act-pair · gpt-3.5-turbo

    key details and metrics related to cycling performances and races

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AIDS
    -0.96
     ACLU
    -0.95
    FBI
    -0.92
    Anonymous
    -0.91
    SCP
    -0.90
    owment
    -0.90
    umblr
    -0.90
    Attorney
    -0.89
    Library
    -0.89
    Sexual
    -0.88
    POSITIVE LOGITS
     tyre
    1.72
     tyres
    1.67
     McLaren
    1.42
     FIA
    1.35
     Renault
    1.35
     racing
    1.34
     braking
    1.32
     Motorsport
    1.31
     manoeuv
    1.30
     Ferrari
    1.29
    Activations Density 0.474%

    No Known Activations