© 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. 4-RES-JB
    11. 23749
    Prev
    Next
    INDEX
    Explanations

    ingredients or food-related terms

    oai_token-act-pair · gpt-3.5-turbo

    sections related to cooking methods or recipes

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

    No Comments

    Negative Logits
     divest
    -0.81
     Wikileaks
    -0.76
     allies
    -0.75
     constitutionally
    -0.74
     assurances
    -0.71
     amnesty
    -0.71
     Arbit
    -0.71
     bloc
    -0.71
     orchestr
    -0.70
     ousted
    -0.69
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.99
    Ingredients
    0.96
    Recipe
    0.94
    Rated
    0.89
    WARNING
    0.88
    ³³³³
    0.87
    Advertisement
    0.87
    ³³
    0.87
    VERTISEMENT
    0.86
    Pros
    0.86
    Activations Density 0.814%

    No Known Activations