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

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-JB
    11. 21730
    Prev
    Next
    INDEX
    Explanations

    keywords related to carbohydrates and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of carbohydrates and low-carb diets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.95
    HCR
    -0.84
    éĹ
    -0.80
    liness
    -0.76
     Shu
    -0.71
     Corruption
    -0.71
    UAL
    -0.69
    Rus
    -0.69
     Generation
    -0.68
     Mayweather
    -0.68
    POSITIVE LOGITS
     carb
    1.30
    ohydrate
    1.20
    carb
    1.07
    ategory
    1.03
    amate
    0.98
    ohyd
    0.97
    uncle
    0.96
     carbs
    0.95
    odic
    0.95
    osponsors
    0.93
    Activations Density 0.009%

    No Known Activations