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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6037
    Prev
    Next
    INDEX
    Explanations

    foods or ingredients

    oai_token-act-pair · gpt-3.5-turbo

    various types of food, elements related to metabolism, and references to health and nutrition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stice
    -0.48
     Nare
    -0.48
     sshd
    -0.47
    emale
    -0.47
     Richards
    -0.43
     ESV
    -0.42
    Knight
    -0.42
     onward
    -0.42
    sis
    -0.42
     Sutherland
    -0.42
    POSITIVE LOGITS
     affili
    0.46
     apiece
    0.42
    padding
    0.41
     caps
    0.40
    matical
    0.39
    atically
    0.39
     pertaining
    0.39
    icing
    0.38
     profiling
    0.38
     related
    0.38
    Activations Density 1.072%

    No Known Activations