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. 9-RES-JB
    6. 12889
    Prev
    Next
    INDEX
    Explanations

    comments or dialogue in text

    oai_token-act-pair · gpt-3.5-turbo

    indicators of document structure or formatting, possibly identifying distinct sections or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suspected
    -0.78
     nationally
    -0.76
     national
    -0.73
     nationwide
    -0.72
     birthplace
    -0.71
     televised
    -0.71
     waged
    -0.70
     alleged
    -0.69
     imprisoned
    -0.69
     embattled
    -0.68
    POSITIVE LOGITS
    edit
    1.10
    Anyway
    1.09
    Quote
    1.09
    Installation
    1.06
    Reviewer
    1.02
    Secondly
    1.01
    Basically
    0.97
    Spoiler
    0.95
    */
    0.94
    prototype
    0.94
    Activations Density 0.647%

    No Known Activations