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. 7-RES-JB
    6. 23197
    Prev
    Next
    INDEX
    Explanations

    references to the University of Ole Miss and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of the word "Ole" in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icho
    -0.75
    ãĤ±
    -0.75
    sch
    -0.69
    journal
    -0.68
     Bosh
    -0.65
    ÙĴ
    -0.64
    iday
    -0.64
    iosis
    -0.64
     Mori
    -0.64
    DOS
    -0.64
    POSITIVE LOGITS
     Tigers
    0.77
    antle
    0.70
    ensical
    0.67
    icester
    0.66
     Vader
    0.65
    poons
    0.65
     Kron
    0.65
    auld
    0.65
     marrow
    0.63
     hitch
    0.62
    Activations Density 0.096%

    No Known Activations