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. 1-RES-JB
    6. 4368
    Prev
    Next
    INDEX
    Explanations

    baseball-related statistics, specifically OPS (On-base Plus Slugging) values

    oai_token-act-pair · gpt-3.5-turbo

    metrics related to sports performance statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bones
    -0.88
    bone
    -0.83
    pox
    -0.77
    ovan
    -0.77
    aja
    -0.76
    ulkan
    -0.73
    assic
    -0.72
    ãĤ©
    -0.70
    cars
    -0.70
    jamin
    -0.69
    POSITIVE LOGITS
    EC
    1.05
     OPS
    0.98
     reluct
    0.94
    enhagen
    0.93
    ilon
    0.84
    cffff
    0.83
    ET
    0.80
    ORTS
    0.80
     ratios
    0.79
    HQ
    0.78
    Activations Density 0.011%

    No Known Activations