© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20700
    Prev
    Next
    INDEX
    Explanations

    nutritional information related to calories, fats, proteins, and other dietary factors

    oai_token-act-pair · gpt-3.5-turbo

    nutritional factors related to calorie content and macronutrients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ker
    -0.73
     Mock
    -0.71
     Siem
    -0.66
    sonian
    -0.66
    DragonMagazine
    -0.65
     Vote
    -0.65
    bara
    -0.64
    ragon
    -0.64
     Honour
    -0.63
    arnaev
    -0.63
    POSITIVE LOGITS
     intake
    1.26
     Intake
    1.11
     intakes
    1.09
     calories
    1.09
     metabolism
    1.05
    ohydrate
    1.02
    aceous
    1.02
    rition
    1.01
     density
    1.01
     expenditure
    1.00
    Activations Density 0.120%

    No Known Activations