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. 7-RES-JB
    6. 10605
    Prev
    Next
    INDEX
    Explanations

    mentions of the letter "C" followed by a single digit number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or term represented by "C" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.74
     Tinder
    -0.71
     Chero
    -0.71
    uyomi
    -0.70
     Yamaha
    -0.65
     Wrestle
    -0.65
    wagen
    -0.63
     htt
    -0.63
     Eston
    -0.62
     juggling
    -0.61
    POSITIVE LOGITS
    overed
    1.28
    abbage
    1.16
    aught
    1.14
    URRENT
    1.14
    ursor
    1.13
    ottage
    1.13
    rouch
    1.10
    rossover
    1.08
    ategor
    1.08
    oding
    1.07
    Activations Density 0.052%

    No Known Activations