© 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. 18676
    Prev
    Next
    INDEX
    Explanations

    Slavic characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    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
     explan
    -0.77
     respons
    -0.75
     laying
    -0.75
     associ
    -0.74
     stripping
    -0.72
     tackling
    -0.70
    chnology
    -0.70
     fragmented
    -0.69
     disenfranch
    -0.68
     endings
    -0.68
    POSITIVE LOGITS
    ãĤ±
    1.01
    ãĥĥãĥī
    0.97
    à¨
    0.95
    ãĥŃ
    0.93
    é¾į
    0.90
    à¥
    0.89
    ¤
    0.88
    CPU
    0.87
    ê
    0.86
    GEN
    0.85
    Activations Density 0.023%

    No Known Activations