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. 4676
    Prev
    Next
    INDEX
    Explanations

    phrases related to awards and titles, specifically "Player of the Year" recipients

    oai_token-act-pair · gpt-3.5-turbo

    mentions of awards, specifically "Player of the Year" titles across various sports

    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
     streng
    -0.74
    sett
    -0.73
    pload
    -0.71
     trave
    -0.71
    hett
    -0.68
     ingred
    -0.67
     arrang
    -0.67
    fram
    -0.66
    uala
    -0.63
    dor
    -0.61
    POSITIVE LOGITS
    iverse
    0.73
    âĦ¢
    0.66
     Awards
    0.65
    elight
    0.63
     Mankind
    0.62
    Copyright
    0.58
     ago
    0.55
    cients
    0.55
     ultr
    0.54
    worms
    0.54
    Activations Density 0.112%

    No Known Activations