© 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. 13666
    Prev
    Next
    INDEX
    Explanations

    food-related terms and ingredients along with cooking techniques

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases related to food and recipes

    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
     Surveillance
    -0.88
     Investig
    -0.81
    Offline
    -0.78
     Networks
    -0.76
     Checking
    -0.74
     Programs
    -0.72
    VIEW
    -0.69
    CLASSIFIED
    -0.68
     Organizations
    -0.68
    PDATE
    -0.68
    POSITIVE LOGITS
     tastes
    1.78
     tasted
    1.61
     taste
    1.60
     cooks
    1.32
     smells
    1.32
     caramel
    1.27
     melts
    1.23
     ferment
    1.23
     flavor
    1.20
     flavored
    1.19
    Activations Density 0.193%

    No Known Activations