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. 2-RES-JB
    6. 2364
    Prev
    Next
    INDEX
    Explanations

    links or references to PDF files

    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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.68
     surn
    -0.64
     Americas
    -0.64
     ages
    -0.63
     roads
    -0.63
     Restaur
    -0.61
     house
    -0.61
    veh
    -0.60
     MVP
    -0.60
     Rye
    -0.60
    POSITIVE LOGITS
    pdf
    1.59
    PDF
    1.35
    DragonMagazine
    1.13
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.95
    TeX
    0.90
     pdf
    0.88
    archive
    0.86
    tar
    0.85
    aneers
    0.85
    herty
    0.82
    Activations Density 0.006%

    No Known Activations