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. 8779
    Prev
    Next
    INDEX
    Explanations

    references to sports events, specifically related to kickoffs and Kickstarters

    oai_token-act-pair · gpt-3.5-turbo

    references to football-related terms, particularly the word "kick."

    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
     abund
    -0.84
    BuyableInstoreAndOnline
    -0.74
     Emin
    -0.74
    Dialogue
    -0.73
    icity
    -0.69
    afety
    -0.68
     Debor
    -0.68
    天
    -0.67
    Else
    -0.67
    icol
    -0.66
    POSITIVE LOGITS
    starter
    1.17
    boxing
    1.05
    strap
    1.01
    starting
    0.98
    started
    0.94
    backs
    0.86
    haw
    0.85
    outs
    0.83
    start
    0.82
    ayne
    0.81
    Activations Density 0.018%

    No Known Activations