© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11257
    Prev
    Next
    INDEX
    Explanations

    contractions of the words "is not"

    oai_token-act-pair · gpt-3.5-turbo

    negations expressed through the contraction "isn't" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERG
    -0.83
    onym
    -0.79
     è£ıè
    -0.71
    stre
    -0.71
    çĶŁ
    -0.70
    onyms
    -0.69
    è¦ļéĨĴ
    -0.68
    èĪ
    -0.68
    onymous
    -0.68
    RON
    -0.67
    POSITIVE LOGITS
     necessarily
    1.12
     exactly
    1.04
     gotta
    0.97
     really
    0.94
     gonna
    0.92
     quite
    0.91
     anymore
    0.90
     even
    0.90
     EVEN
    0.85
     bluff
    0.83
    Activations Density 0.094%

    No Known Activations