© 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. 10-RES-JB
    11. 16656
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooking instructions and food preparation

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to cooking instructions and methods

    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
    href
    -0.81
     Surveillance
    -0.78
     Transgender
    -0.77
     Paran
    -0.76
    Events
    -0.75
    Tele
    -0.74
     Valiant
    -0.72
     DACA
    -0.72
     Vehicles
    -0.70
     Gamergate
    -0.70
    POSITIVE LOGITS
     cooked
    1.50
     crispy
    1.49
     overc
    1.48
     cooks
    1.40
     flavorful
    1.39
     roasted
    1.39
     caramel
    1.35
     seasoning
    1.34
     flavor
    1.34
     juices
    1.33
    Activations Density 0.334%

    No Known Activations