© 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. 0-RES-JB
    11. 16355
    Prev
    Next
    INDEX
    Explanations

    references related to a specific numerical value (420)

    oai_token-act-pair · gpt-3.5-turbo

    references to the number "420."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WATCHED
    -0.73
    ibling
    -0.72
     Franch
    -0.71
     Insert
    -0.68
     Simone
    -0.67
    tracks
    -0.66
     Fernand
    -0.64
     IMAGES
    -0.64
     Simmons
    -0.61
     Wage
    -0.61
    POSITIVE LOGITS
    420
    2.57
     420
    1.46
     Bohem
    1.11
    2020
    1.01
    450
    0.97
    cake
    0.95
    422
    0.94
    421
    0.88
    419
    0.88
    weed
    0.87
    Activations Density 0.015%

    No Known Activations