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. 11-RES-JB
    6. 663
    Prev
    Next
    INDEX
    Explanations

    JavaScript programming language terms related to database operations

    oai_token-act-pair · gpt-3.5-turbo

    programming syntax and structure in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pir
    -0.77
     quo
    -0.76
     rocking
    -0.75
     aided
    -0.70
     elusive
    -0.69
     persecuted
    -0.69
     sparing
    -0.68
     buoy
    -0.68
     dared
    -0.67
     feared
    -0.66
    POSITIVE LOGITS
    append
    1.42
    prototype
    1.41
    apply
    1.39
    remove
    1.35
    create
    1.34
    replace
    1.33
    split
    1.31
    find
    1.30
    clone
    1.29
    push
    1.29
    Activations Density 0.047%

    No Known Activations