© 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. 0-RES-JB
    11. 11387
    Prev
    Next
    INDEX
    Explanations

    instances of the word "log"

    oai_token-act-pair · gpt-3.5-turbo

    references to logging or logs in various contexts

    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
     Blasio
    -0.83
     Bucks
    -0.74
    rael
    -0.73
     Haram
    -0.73
    Īè
    -0.73
     Cyrus
    -0.71
    hur
    -0.71
    araoh
    -0.71
    uron
    -0.69
     Piercing
    -0.68
    POSITIVE LOGITS
     log
    3.68
     logs
    2.63
     Log
    2.50
    log
    2.33
     logging
    2.26
    Log
    2.22
     LOG
    1.97
     logged
    1.83
     logger
    1.74
    LOG
    1.67
    Activations Density 0.007%

    No Known Activations