© 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. 8-RES-JB
    11. 17585
    Prev
    Next
    INDEX
    Explanations

    strings of characters that symbolize actions or reactions in a conversation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "âĢ" followed by various forms of expressed sentiments or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marketable
    -0.78
     Reprodu
    -0.71
     Panc
    -0.71
    erous
    -0.69
    eer
    -0.68
    swick
    -0.67
     Chatt
    -0.64
     Settlement
    -0.63
    creen
    -0.62
    ously
    -0.62
    POSITIVE LOGITS
    ª
    1.18
    ł
    1.14
    ij
    0.98
    IJ
    0.90
    ¤
    0.89
    ¹
    0.88
    ¡
    0.87
    Insert
    0.86
    ı
    0.84
    «
    0.83
    Activations Density 0.138%

    No Known Activations