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. 18353
    Prev
    Next
    INDEX
    Explanations

    references to body parts, especially fingers

    oai_token-act-pair · gpt-3.5-turbo

    the various contexts in which hands and fingers are mentioned

    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
    nance
    -0.72
    ItemImage
    -0.72
     Vide
    -0.70
    BUG
    -0.67
    nce
    -0.67
    rama
    -0.66
    âĸ¬
    -0.65
     Serious
    -0.61
    inem
    -0.61
     Proposition
    -0.61
    POSITIVE LOGITS
    mith
    1.47
    pring
    1.34
    creen
    1.29
    heet
    1.12
    cape
    1.04
    hips
    1.04
    hops
    1.02
    paces
    1.02
    hift
    1.02
    peed
    1.02
    Activations Density 0.055%

    No Known Activations