© 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. 10-RES-JB
    11. 19055
    Prev
    Next
    INDEX
    Explanations

    descriptions of various types of preparation methods and ingredients in recipes

    oai_token-act-pair · gpt-3.5-turbo

    references to types of food, particularly meat and snacks

    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
     Infrastructure
    -0.92
    atform
    -0.84
    Asset
    -0.83
    Financial
    -0.80
     UNCLASSIFIED
    -0.77
    rastructure
    -0.76
     Networks
    -0.76
     Funding
    -0.75
    funding
    -0.74
    Platform
    -0.74
    POSITIVE LOGITS
     herbal
    1.13
     aromatic
    1.11
     edible
    1.10
     moist
    1.05
     herbs
    1.04
     scent
    1.04
     carniv
    1.03
     recipes
    1.03
     culinary
    1.03
     vegetarian
    1.03
    Activations Density 0.915%

    No Known Activations