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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14154
    Prev
    Next
    INDEX
    Explanations

    recipes and cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements typically used in cooking or recipes

    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
    ENC
    -0.73
    itably
    -0.70
     intrins
    -0.66
    achus
    -0.64
    arlane
    -0.64
    549
    -0.61
    antis
    -0.61
    achu
    -0.60
    olis
    -0.60
    plays
    -0.59
    POSITIVE LOGITS
    ths
    1.17
     teaspoon
    1.06
     cup
    1.02
     inch
    0.99
     tsp
    0.97
     ounce
    0.95
    rd
    0.89
     mile
    0.89
    âĢ³
    0.89
     gallon
    0.86
    Activations Density 0.051%

    No Known Activations