© 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 EvalsExportsAPI 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. 8-RES-JB
    11. 22405
    Prev
    Next
    INDEX
    Explanations

    mentions of sports competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to different sports cups and tournaments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.79
    izabeth
    -0.77
     obser
    -0.74
    paio
    -0.74
    anim
    -0.74
    oidal
    -0.73
    arily
    -0.73
    echo
    -0.72
    sbm
    -0.70
    apses
    -0.69
    POSITIVE LOGITS
     Playoffs
    1.17
     Winners
    1.15
     Playoff
    1.13
    cake
    1.12
    cakes
    1.11
     Finals
    0.97
     playoffs
    0.95
     winners
    0.91
     finals
    0.86
     Championships
    0.85
    Activations Density 0.030%

    No Known Activations