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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 1171
    Prev
    Next
    INDEX
    Explanations

    jersey numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to jerseys, specifically focusing on their characteristics and rules related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.78
    ths
    -0.76
    speech
    -0.75
    cause
    -0.74
    lishes
    -0.72
    demon
    -0.71
    moderate
    -0.70
    irlf
    -0.70
    slow
    -0.70
    edient
    -0.69
    POSITIVE LOGITS
     jersey
    1.23
     jerseys
    1.11
    seys
    0.98
     sleeve
    0.81
     sweater
    0.80
     sleeves
    0.79
     tint
    0.77
     worn
    0.74
     shirt
    0.73
     sponsorship
    0.73
    Activations Density 0.006%

    No Known Activations