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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 18099
    Prev
    Next
    INDEX
    Explanations

    words related to delicate and intricate things

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "delicate" and related terms describing subtlety or finesse

    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
     Gutenberg
    -0.92
    GW
    -0.71
    imaru
    -0.66
     Shelter
    -0.66
     Homeless
    -0.64
     Dayton
    -0.63
    isSpecialOrderable
    -0.63
    Support
    -0.62
     disbanded
    -0.61
     Generator
    -0.61
    POSITIVE LOGITS
     delic
    1.11
    istry
    1.10
     sensibilities
    0.98
     delicate
    0.95
     nuances
    0.92
     intric
    0.88
    ately
    0.87
     nuance
    0.87
     precision
    0.86
    acies
    0.85
    Activations Density 0.045%

    No Known Activations