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. 7-RES-JB
    6. 20106
    Prev
    Next
    INDEX
    Explanations

    words related to clothing, specifically jerseys

    oai_token-act-pair · gpt-3.5-turbo

    references to jerseys in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llor
    -0.81
    inez
    -0.80
    yrinth
    -0.79
    ushima
    -0.78
    moderate
    -0.77
    enthal
    -0.76
    cause
    -0.76
    romy
    -0.76
    course
    -0.75
    sth
    -0.75
    POSITIVE LOGITS
     worn
    1.12
     jerseys
    1.08
     jersey
    1.01
     sleeve
    0.92
    seys
    0.91
     sleeves
    0.91
     tint
    0.85
     adorned
    0.85
     sweater
    0.78
     insign
    0.77
    Activations Density 0.020%

    No Known Activations