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. 9721
    Prev
    Next
    INDEX
    Explanations

    references to manuals or technical documentation

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of manuals and diagnostic tools

    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
    venge
    -0.71
    bucks
    -0.70
    orate
    -0.69
    cffff
    -0.69
    cedented
    -0.68
    ments
    -0.67
     Canary
    -0.65
    timeout
    -0.65
    ĪĴ
    -0.65
    paren
    -0.65
    POSITIVE LOGITS
     manuscript
    0.92
     vit
    0.91
     detailing
    0.91
     pages
    0.89
     edition
    0.89
     outlining
    0.89
     editors
    0.88
     entries
    0.86
     booklet
    0.86
     entry
    0.84
    Activations Density 0.098%

    No Known Activations