© 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. 9-RES-JB
    11. 2501
    Prev
    Next
    INDEX
    Explanations

    references to mealtime activities or food, specifically focusing on lunch

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignty
    -0.70
     Painter
    -0.66
     Proposition
    -0.65
     CSI
    -0.62
     Judd
    -0.60
    女
    -0.60
     Exile
    -0.60
     Jed
    -0.60
     leverage
    -0.57
     persecution
    -0.57
    POSITIVE LOGITS
    worms
    1.19
    time
    1.17
    bowl
    1.04
     buffet
    1.01
    worm
    1.00
     meal
    0.99
    wich
    0.96
     meals
    0.94
    aturday
    0.93
    table
    0.89
    Activations Density 0.060%

    No Known Activations