© 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. 7766
    Prev
    Next
    INDEX
    Explanations

    the word "ì" with a strong activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific characters or symbols

    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
     rog
    -0.76
     rake
    -0.68
     rolling
    -0.63
     Gn
    -0.63
     Wallace
    -0.62
     Warden
    -0.62
     Roll
    -0.61
     roll
    -0.61
     rogue
    -0.60
     wider
    -0.59
    POSITIVE LOGITS
    à¤
    2.40
    ì
    2.04
    à¨
    0.96
    ãĥ³
    0.95
     Kuala
    0.92
    Ñģ
    0.92
    ãĥĬ
    0.90
    à¦
    0.88
     Haj
    0.86
     ì
    0.85
    Activations Density 0.006%

    No Known Activations