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. 9121
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to small or miniature objects or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to small or diminutive items or concepts, particularly related to the word "itty."

    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
    xual
    -0.87
    ppelin
    -0.85
    isco
    -0.80
    oway
    -0.79
    omen
    -0.77
    ovie
    -0.74
    ese
    -0.74
    ications
    -0.73
    indal
    -0.73
    orescence
    -0.73
    POSITIVE LOGITS
    abyte
    0.82
    bilt
    0.81
     litter
    0.81
     tract
    0.79
    abytes
    0.78
    ãĤ¡
    0.72
     Pry
    0.72
     gritty
    0.71
    gets
    0.70
    ãĤ´
    0.68
    Activations Density 0.032%

    No Known Activations