Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7362
    Prev
    Next
    INDEX
    Explanations

    athletes who were selected in the fourth round of drafts

    oai_token-act-pair · gpt-3.5-turbo

    references to draft picks in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Andersen
    -0.73
     dermat
    -0.65
     pers
    -0.64
    İĭ
    -0.63
     Evangel
    -0.61
     Kane
    -0.61
     Engel
    -0.60
     appar
    -0.60
     aided
    -0.60
     Klein
    -0.59
    POSITIVE LOGITS
    round
    4.21
    rounder
    2.61
    Round
    2.29
    rounded
    1.95
     round
    1.92
     rounds
    1.73
     Round
    1.67
     Rounds
    1.64
    around
    1.44
    stage
    1.12
    Activations Density 0.017%

    No Known Activations