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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23247
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and statistics, specifically related to scoring, pitching, rushing, and shooting

    oai_token-act-pair · gpt-3.5-turbo

    sports-related terms and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idon
    -0.84
    imus
    -0.79
    gro
    -0.79
    nery
    -0.78
    ighed
    -0.78
    els
    -0.76
    efer
    -0.75
    nee
    -0.74
    iphany
    -0.73
    zz
    -0.73
    POSITIVE LOGITS
     prowess
    1.11
     ability
    0.95
     talent
    0.89
     capability
    0.86
     peripher
    0.82
     abilities
    0.81
     capacity
    0.81
     capabilities
    0.81
     chops
    0.80
     inept
    0.80
    Activations Density 0.127%

    No Known Activations