© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4132
    Prev
    Next
    INDEX
    Explanations

    sporting achievements and titles such as championships, cups, and trophies

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable achievements in sports

    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
    oke
    -0.87
    okes
    -0.79
    oked
    -0.78
    bugs
    -0.74
    source
    -0.73
    rays
    -0.72
    chan
    -0.71
    scan
    -0.70
    react
    -0.70
    rish
    -0.70
    POSITIVE LOGITS
     championships
    1.23
     championship
    1.18
     Finals
    1.17
     postseason
    1.16
     Champions
    1.14
     playoffs
    1.13
     medals
    1.12
     Championships
    1.08
     trophies
    1.08
     playoff
    1.07
    Activations Density 0.389%

    No Known Activations