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. 7-RES-JB
    6. 4193
    Prev
    Next
    INDEX
    Explanations

    terms related to dietary fats, specifically saturated fats

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dietary fats and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    shire
    -0.80
    ison
    -0.71
     Mub
    -0.71
    ski
    -0.70
    ground
    -0.69
    uci
    -0.67
    axis
    -0.67
    legate
    -0.65
    asser
    -0.64
    RL
    -0.64
    POSITIVE LOGITS
     fats
    0.95
     fatty
    0.83
     acids
    0.74
    tti
    0.69
     straw
    0.68
     triglycer
    0.68
     tuna
    0.67
    ////////////////////////////////
    0.67
     oils
    0.66
     punch
    0.66
    Activations Density 0.083%

    No Known Activations