Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5446
    Prev
    Next
    INDEX
    Explanations

    references to technical terms related to technology, specifically "Pixel."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Pixel."

    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
    tro
    -0.75
    een
    -0.75
    tra
    -0.75
     Stew
    -0.73
     stew
    -0.72
    anship
    -0.71
     stag
    -0.70
    argo
    -0.70
    cohol
    -0.68
     welfare
    -0.68
    POSITIVE LOGITS
     Pixel
    4.11
    Pixel
    2.92
    pixel
    2.01
     pixel
    1.67
     Nexus
    1.51
    ixels
    1.50
     Chromebook
    1.44
     Xperia
    1.39
     OnePlus
    1.37
     Lumia
    1.28
    Activations Density 0.015%

    No Known Activations