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. 3856
    Prev
    Next
    INDEX
    Explanations

    PDF files or references to PDFs

    oai_token-act-pair · gpt-3.5-turbo

    references to PDF documents

    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
    places
    -0.79
    odka
    -0.78
    opoulos
    -0.76
    venge
    -0.75
    oglu
    -0.69
    leep
    -0.67
    ccoli
    -0.66
    taboola
    -0.66
    powers
    -0.66
    abouts
    -0.65
    POSITIVE LOGITS
    PDF
    1.22
     format
    1.12
     file
    1.08
     Format
    1.05
     PDF
    1.03
     version
    1.02
    pdf
    1.01
    TeX
    0.99
    DragonMagazine
    0.99
    Reader
    0.97
    Activations Density 0.034%

    No Known Activations