Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16930
    Prev
    Next
    INDEX
    Explanations

    specific symbols or markers

    oai_token-act-pair · gpt-3.5-turbo

    symbols that represent special characters or formatting in text

    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
    conn
    -0.83
    oké
    -0.79
    zbek
    -0.74
    repre
    -0.73
    abl
    -0.73
    opian
    -0.70
    osh
    -0.70
    orters
    -0.69
    jack
    -0.68
    ibly
    -0.68
    POSITIVE LOGITS
     Various
    1.07
     Provides
    1.07
     Completed
    1.06
     Featuring
    1.03
     Introduction
    1.02
     [|
    1.02
     Announce
    1.02
     Contains
    0.99
     Died
    0.99
     Miscellaneous
    0.98
    Activations Density 0.090%

    No Known Activations