© 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. 11-RES-JB
    11. 1332
    Prev
    Next
    INDEX
    Explanations

    the word "but" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but" indicating contrast or exception

    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
     pione
    -0.88
    Ě
    -0.81
    ā
    -0.81
     externalTo
    -0.81
    ē
    -0.81
    ė
    -0.81
    ğ
    -0.81
    č
    -0.81
    À
    -0.80
    ÷
    -0.80
    POSITIVE LOGITS
     alas
    1.15
     unfortunately
    0.94
     nowhere
    0.93
     beware
    0.93
     nevertheless
    0.93
     unless
    0.91
     realistically
    0.88
     surely
    0.87
     nonetheless
    0.86
     why
    0.85
    Activations Density 0.157%

    No Known Activations