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. 8-RES-JB
    6. 4418
    Prev
    Next
    INDEX
    Explanations

    Python code patterns related to Django

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods and the use of colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fargo
    -0.72
     Patron
    -0.70
     Emmy
    -0.69
     looph
    -0.68
     surpr
    -0.68
     knowing
    -0.68
     raced
    -0.67
     Marino
    -0.67
     ADA
    -0.67
     Mara
    -0.66
    POSITIVE LOGITS
    utils
    1.33
    dll
    1.29
    plugins
    1.29
    github
    1.25
    exe
    1.23
    sys
    1.23
    tools
    1.22
    modules
    1.22
    dev
    1.17
    edu
    1.16
    Activations Density 0.139%

    No Known Activations