© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 2047
    Prev
    Next
    INDEX
    Explanations

    special characters in text, specifically focusing on the Unicode characters "Â" and "ĵ"

    oai_token-act-pair · gpt-3.5-turbo

    special characters or accented letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.67
    ãģ®éŃĶ
    -0.65
     Kag
    -0.65
     Sidd
    -0.64
    ographers
    -0.63
     comprehens
    -0.63
     Mamm
    -0.63
     recommended
    -0.63
    enburg
    -0.62
     Apollo
    -0.61
    POSITIVE LOGITS
    ¿
    1.74
    ¹
    1.71
    ¾
    1.71
    ´
    1.68
    ¼
    1.68
    ¦
    1.65
    ¨
    1.64
    ³
    1.64
    ¬
    1.63
    ¤
    1.62
    Activations Density 0.015%

    No Known Activations