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. 0-RES-JB
    6. 24030
    Prev
    Next
    INDEX
    Explanations

    alphanumeric character sequences with special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unusual symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grunt
    -0.71
     Blair
    -0.70
     Scorp
    -0.69
     popcorn
    -0.68
     plat
    -0.67
     disabled
    -0.67
     Weston
    -0.66
     Dalton
    -0.65
     scroll
    -0.65
     glut
    -0.63
    POSITIVE LOGITS
    Ã
    4.23
    Ä
    1.99
    Ãī
    1.91
    Ãį
    1.86
    ó
    1.86
     Ã
    1.82
    Å
    1.81
    Ãĥ
    1.78
    ÃŃ
    1.76
    Ç
    1.67
    Activations Density 0.006%

    No Known Activations