Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 24217
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Bol"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Bol" or similar variations, likely indicating a focus on a specific person or entity associated with that term

    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
    PRESS
    -0.67
     Legends
    -0.62
    natureconservancy
    -0.61
    esis
    -0.61
    ellen
    -0.58
     ROCK
    -0.58
     rounding
    -0.57
    backer
    -0.56
     Argon
    -0.56
    æĸ¹
    -0.55
    POSITIVE LOGITS
    ivia
    1.04
    thouse
    0.97
    uca
    0.94
    sh
    0.88
    lett
    0.87
    zar
    0.86
    atility
    0.82
    ts
    0.81
    umes
    0.80
    sha
    0.80
    Activations Density 0.019%

    No Known Activations