© 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. 2688
    Prev
    Next
    INDEX
    Explanations

    references to the Thanksgiving holiday, including related activities and traditions

    oai_token-act-pair · gpt-3.5-turbo

    references to Thanksgiving and its associated foods

    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
    inel
    -0.88
    anmar
    -0.77
    estial
    -0.76
    umbai
    -0.75
    andro
    -0.75
    ei
    -0.75
    andr
    -0.74
    ial
    -0.73
    uno
    -0.73
    uckland
    -0.72
    POSITIVE LOGITS
     pancakes
    0.90
     fries
    0.88
     starch
    0.88
     dinners
    0.85
     burgers
    0.83
     turkey
    0.82
     bake
    0.80
     potatoes
    0.80
     Potato
    0.80
     potato
    0.78
    Activations Density 0.062%

    No Known Activations