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. 23252
    Prev
    Next
    INDEX
    Explanations

    numbers related to points, goals, and scoring in various contexts such as sports or games

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to scoring in sports

    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
    folk
    -0.70
    aucuses
    -0.68
    rish
    -0.62
    feature
    -0.60
    ilic
    -0.60
    atem
    -0.60
     Strait
    -0.59
    holder
    -0.58
    affer
    -0.57
    sembly
    -0.57
    POSITIVE LOGITS
     consecutive
    1.04
    aciously
    0.93
     percent
    0.87
     million
    0.84
     kilograms
    0.80
     tons
    0.80
     fewer
    0.79
    ½
    0.79
     additional
    0.79
     ounces
    0.78
    Activations Density 0.197%

    No Known Activations