© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 11948
    Prev
    Next
    INDEX
    Explanations

    terms related to fats and nutrition, particularly focusing on saturated fats

    oai_token-act-pair · gpt-3.5-turbo

    references to saturated fat and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gotten
    -0.80
    repair
    -0.72
    fits
    -0.69
    bats
    -0.66
    unit
    -0.66
    runner
    -0.65
    wright
    -0.63
    stand
    -0.61
    DragonMagazine
    -0.61
    shire
    -0.61
    POSITIVE LOGITS
     fats
    0.98
    aturated
    0.92
    quished
    0.82
    antha
    0.80
     fatty
    0.80
    xual
    0.75
     saturated
    0.72
    creen
    0.71
    ategory
    0.70
    inity
    0.68
    Activations Density 0.045%

    No Known Activations