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. 8-RES-JB
    6. 4473
    Prev
    Next
    INDEX
    Explanations

    words related to being a runner-up or participant in a competition

    oai_token-act-pair · gpt-3.5-turbo

    references to runners, specifically in a racing or competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rification
    -0.75
    olia
    -0.73
     ILCS
    -0.71
    illery
    -0.70
     holdings
    -0.70
    rox
    -0.69
    inian
    -0.65
     Debor
    -0.63
     Bureau
    -0.63
    orescent
    -0.63
    POSITIVE LOGITS
    ners
    0.97
    swick
    0.92
    wear
    0.87
    gaard
    0.85
    runner
    0.84
    ways
    0.84
    bum
    0.80
    nings
    0.79
    pants
    0.79
     stitch
    0.78
    Activations Density 0.028%

    No Known Activations