© 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. 6-RES-JB
    11. 13709
    Prev
    Next
    INDEX
    Explanations

    action words related to dining or eating

    oai_token-act-pair · gpt-3.5-turbo

    mentions of dining and meal-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vaj
    -0.76
     Rowling
    -0.71
     Caldwell
    -0.69
     Constable
    -0.68
    RFC
    -0.68
     TJ
    -0.67
     notch
    -0.66
     pivot
    -0.66
     WB
    -0.65
     Judd
    -0.65
    POSITIVE LOGITS
     meals
    1.19
    Food
    1.09
     foods
    0.99
    food
    0.98
     meal
    0.98
     snacks
    0.96
     nutritious
    0.96
     food
    0.96
     beverage
    0.95
     beverages
    0.94
    Activations Density 0.274%

    No Known Activations