© 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. 1-RES-JB
    11. 20381
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to code or programming, specifically focusing on the term 'ssl'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "sl" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®éŃĶ
    -0.93
    ICLE
    -0.87
    enegger
    -0.78
    NEY
    -0.75
     unfocusedRange
    -0.71
    æĦ
    -0.67
     GAME
    -0.66
     EDITION
    -0.65
    éļ
    -0.65
    RON
    -0.65
    POSITIVE LOGITS
    ashes
    0.98
    ips
    0.97
    aughter
    0.96
    ash
    0.96
    ideshow
    0.95
    inking
    0.95
    ngth
    0.94
    udge
    0.93
    ither
    0.93
    anguage
    0.91
    Activations Density 0.008%

    No Known Activations