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. 10280
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports, including leading categories and achievements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sports teams, leagues, and their performance metrics

    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
    assets
    -0.66
    fy
    -0.64
     condol
    -0.64
     lett
    -0.63
    oshenko
    -0.62
    doi
    -0.62
    onday
    -0.61
     srfAttach
    -0.61
     Majesty
    -0.61
    bek
    -0.59
    POSITIVE LOGITS
    arez
    0.86
    udic
    0.82
    inki
    0.80
    ggle
    0.77
    ardless
    0.77
    athlon
    0.74
    uberty
    0.74
    enium
    0.73
    way
    0.72
    roller
    0.70
    Activations Density 0.161%

    No Known Activations