© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11156
    Prev
    Next
    INDEX
    Explanations

    information related to time durations and serving sizes in recipes

    oai_token-act-pair · gpt-3.5-turbo

    cooking-related time and measurement information

    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
     fuzz
    -0.81
     crypt
    -0.73
    uras
    -0.72
    76561
    -0.68
     reinstated
    -0.67
     hay
    -0.66
     loudspe
    -0.65
     resid
    -0.64
     unic
    -0.63
     helium
    -0.63
    POSITIVE LOGITS
     Ingredients
    1.06
     Recipe
    1.05
     Prep
    1.04
     Cook
    0.95
     Course
    0.90
     Instructions
    0.87
    Prep
    0.87
    Cook
    0.84
    isine
    0.81
     Cooking
    0.81
    Activations Density 0.040%

    No Known Activations