© 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. 10-RES-JB
    11. 10548
    Prev
    Next
    INDEX
    Explanations

    references to video games and software platforms like Steam and lightweight game development engines

    oai_token-act-pair · gpt-3.5-turbo

    parentheses in the text

    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
     gaze
    -0.83
     hydrogen
    -0.78
     soaking
    -0.78
     wrinkles
    -0.77
     perme
    -0.76
     whiskey
    -0.73
     spir
    -0.73
     swell
    -0.72
     peanut
    -0.72
     watering
    -0.72
    POSITIVE LOGITS
    formerly
    1.49
    includes
    1.43
    feat
    1.38
    optional
    1.32
    Main
    1.31
    Single
    1.31
    2009
    1.30
    2011
    1.30
    ...)
    1.30
    BBC
    1.30
    Activations Density 0.097%

    No Known Activations