© 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. 18666
    Prev
    Next
    INDEX
    Explanations

    symbols, underscores, and technical formatting commonly found in data or code

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols, separators, or patterns 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
     divers
    -0.82
    oms
    -0.71
    tons
    -0.67
     biologists
    -0.65
     Bald
    -0.65
     disg
    -0.63
     saline
    -0.63
     Syri
    -0.62
     poaching
    -0.62
    ered
    -0.62
    POSITIVE LOGITS
    _______
    1.85
    ______
    1.82
    _____
    1.70
    ________
    1.68
    ________________
    1.68
    ____
    1.66
    ___
    1.59
    ________________________
    1.56
    __
    1.46
    _.
    1.26
    Activations Density 0.022%

    No Known Activations