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. 9813
    Prev
    Next
    INDEX
    Explanations

    legal and institutional terms related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rights, protections, and cultural or community-related concepts

    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
    İ
    -0.66
    Ĭ±
    -0.66
    ady
    -0.60
    ":"/
    -0.59
    GAN
    -0.58
    Ĥª
    -0.58
    Į
    -0.57
    é¾į
    -0.56
    ._
    -0.55
    ICH
    -0.55
    POSITIVE LOGITS
     etc
    1.67
    etc
    1.43
     and
    1.13
     &
    1.04
     ect
    0.95
     or
    0.89
     et
    0.88
    and
    0.85
    whatever
    0.84
     AND
    0.81
    Activations Density 0.215%

    No Known Activations