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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3969
    Prev
    Next
    INDEX
    Explanations

    newsworthy locations or events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically parentheses and periods

    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
    fen
    -0.64
    antha
    -0.62
     untouched
    -0.62
    oooooooooooooooo
    -0.61
    azon
    -0.61
     overw
    -0.60
    yrus
    -0.59
    fruit
    -0.58
     blo
    -0.58
     stabil
    -0.57
    POSITIVE LOGITS
     --
    0.82
     âĢķ
    0.73
     Investigators
    0.73
     Retrieved
    0.72
     ®
    0.71
     Tonight
    0.71
     >>
    0.71
     –
    0.69
    esm
    0.69
     ---
    0.67
    Activations Density 0.037%

    No Known Activations