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. 6-RES-JB
    6. 3989
    Prev
    Next
    INDEX
    Explanations

    mentions related to the sport of boxing, such as boxers' names, events, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to boxing and boxers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dfx
    -0.93
    gency
    -0.84
    UTC
    -0.83
    imates
    -0.78
    kson
    -0.73
     Archdemon
    -0.73
    adian
    -0.72
     AFB
    -0.72
    chev
    -0.72
    rian
    -0.70
    POSITIVE LOGITS
     boxing
    0.97
     Boxing
    0.92
    bowl
    0.87
    eers
    0.85
    fighters
    0.80
     gloves
    0.79
     glove
    0.77
     boxer
    0.77
     corrid
    0.74
     gym
    0.73
    Activations Density 0.021%

    No Known Activations