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. 10-RES-JB
    6. 9817
    Prev
    Next
    INDEX
    Explanations

    names or initials starting with the letter "C" followed by a possible middle initial or name that include the letter "C" and a number designation

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'C' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lur
    -0.68
     Chero
    -0.67
     GOODMAN
    -0.65
    uyomi
    -0.64
     thanks
    -0.64
     err
    -0.64
     bottleneck
    -0.64
     longer
    -0.62
     upward
    -0.61
     Tinder
    -0.61
    POSITIVE LOGITS
    esar
    1.34
    actus
    1.24
    auldron
    1.20
    rossover
    1.20
    URRENT
    1.19
    overed
    1.18
    abbage
    1.17
    ategor
    1.16
    ottage
    1.16
    ripp
    1.16
    Activations Density 0.044%

    No Known Activations