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. 7204
    Prev
    Next
    INDEX
    Explanations

    requests for financial support or donations

    oai_token-act-pair · gpt-3.5-turbo
    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
     largeDownload
    -0.69
    ktop
    -0.66
    yip
    -0.63
    igslist
    -0.61
    fecture
    -0.61
    ãĤ´ãĥ³
    -0.61
     Argon
    -0.60
    pection
    -0.58
    arts
    -0.58
    geist
    -0.58
    POSITIVE LOGITS
    llular
    0.63
    SPONSORED
    0.59
    encies
    0.57
    iencies
    0.56
    osity
    0.56
    usra
    0.55
    obal
    0.54
    ema
    0.54
    onian
    0.53
    Mid
    0.53
    Activations Density 0.038%

    No Known Activations