© 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. 18495
    Prev
    Next
    INDEX
    Explanations

    randomly generated sequences of special characters

    oai_token-act-pair · gpt-3.5-turbo

    the symbol "âĢ" which appears multiple times, indicating a focus on specific formatting or encoding issues

    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
     Thomson
    -0.88
     Tob
    -0.77
     Jem
    -0.74
     mathemat
    -0.73
    itsch
    -0.72
     hypert
    -0.68
     Wer
    -0.68
     Wichita
    -0.68
     Skydragon
    -0.68
     telev
    -0.68
    POSITIVE LOGITS
    Ļ
    2.00
    ħ
    1.40
    ¬
    1.30
    ĺ
    1.29
    ı
    1.21
    ĸ
    1.20
    ļ
    1.20
    ¤
    1.19
    Ĩ
    1.15
    ¡
    1.14
    Activations Density 0.330%

    No Known Activations