© 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. 10-RES-JB
    11. 10226
    Prev
    Next
    INDEX
    Explanations

    terms related to nutritional content, specifically focusing on calories and fats

    oai_token-act-pair · gpt-3.5-turbo

    terms relating to calorie and nutritional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    smanship
    -0.83
    kus
    -0.74
    idable
    -0.73
     Cthulhu
    -0.69
    ker
    -0.68
    76561
    -0.67
    agall
    -0.66
     Cosponsors
    -0.65
    jun
    -0.65
    bara
    -0.65
    POSITIVE LOGITS
     calories
    1.19
    ohydrate
    1.19
     intake
    1.19
    rition
    1.16
    ritional
    1.14
     diet
    1.14
    orie
    1.13
     carbs
    1.07
     intakes
    1.06
     nutrition
    1.05
    Activations Density 0.052%

    No Known Activations