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. 5-RES-JB
    6. 5954
    Prev
    Next
    INDEX
    Explanations

    disclaimers and statements indicating that opinions expressed are not necessarily those of a larger entity

    oai_token-act-pair · gpt-3.5-turbo

    statements of caution or disclaimers regarding opinions expressed by individuals or participants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     taps
    -0.73
    milo
    -0.73
    aunts
    -0.73
    ghazi
    -0.71
     manifold
    -0.67
    chio
    -0.66
    gered
    -0.66
    INTON
    -0.65
    Mot
    -0.62
     Sabha
    -0.62
    POSITIVE LOGITS
     disclaimer
    0.96
     disclaim
    0.89
     editorial
    0.88
     copyright
    0.86
     trademark
    0.84
     trademarks
    0.84
     copyrighted
    0.83
     strictly
    0.81
     privacy
    0.80
     NOTICE
    0.80
    Activations Density 0.768%

    No Known Activations