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. 22353
    Prev
    Next
    INDEX
    Explanations

    mention of sports competitions and match outcomes

    oai_token-act-pair · gpt-3.5-turbo

    actions related to competitive confrontations or matches, particularly in sports contexts

    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
    oun
    -0.78
    account
    -0.77
    ridges
    -0.76
    iscal
    -0.75
    paralle
    -0.73
    arse
    -0.73
    quist
    -0.72
    aird
    -0.71
    acea
    -0.71
    imen
    -0.71
    POSITIVE LOGITS
     him
    0.84
     fellow
    0.78
     RHP
    0.76
     opponents
    0.73
     captains
    0.71
     hordes
    0.71
     undefeated
    0.70
     unbeaten
    0.69
     opponent
    0.68
     finalists
    0.68
    Activations Density 0.099%

    No Known Activations