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. 21175
    Prev
    Next
    INDEX
    Explanations

    punctuated citations or attributions in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    semicolons indicating the end of a section or a contributor in text

    oai_token-act-pair · gpt-3.5-turbo
    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
     resil
    -0.69
    hof
    -0.68
    vals
    -0.66
     helicop
    -0.66
     unnecess
    -0.65
    stration
    -0.63
     trou
    -0.62
    ovy
    -0.62
    icum
    -0.62
     psychiat
    -0.62
    POSITIVE LOGITS
    -)
    1.12
    alias
    0.89
     alternatively
    0.82
     Editing
    0.79
     cf
    0.77
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.75
     thence
    0.68
     Owner
    0.67
    hester
    0.66
     Inher
    0.64
    Activations Density 0.037%

    No Known Activations