© 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. 13860
    Prev
    Next
    INDEX
    Explanations

    words that suggest a contrast or exception in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "But" indicating a contrast or shift in the narrative

    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
     comm
    -0.64
     complete
    -0.61
    ile
    -0.56
     continuously
    -0.55
     favorably
    -0.55
     approximately
    -0.54
     commence
    -0.54
     generally
    -0.54
     classified
    -0.54
     randomly
    -0.53
    POSITIVE LOGITS
     But
    2.73
    But
    2.19
     Yet
    1.92
     However
    1.88
    but
    1.76
     BUT
    1.65
     And
    1.63
    BUT
    1.63
     Nevertheless
    1.60
    Yet
    1.59
    Activations Density 0.058%

    No Known Activations