© 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. 1-RES-JB
    11. 21555
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find the word "Not"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Not" emphasizing negation or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assetsadobe
    -0.75
    ãĤ¼ãĤ¦ãĤ¹
    -0.74
    CRIP
    -0.69
    大
    -0.69
    stakes
    -0.69
    ç·
    -0.67
    éĥ
    -0.67
    è¦ļéĨĴ
    -0.67
     metre
    -0.67
    ERY
    -0.66
    POSITIVE LOGITS
    epad
    1.20
    withstanding
    1.18
    icably
    1.09
     necessarily
    1.09
    eworthy
    1.01
    orious
    1.00
    ices
    1.00
    ifications
    0.92
    theless
    0.88
     Tradable
    0.87
    Activations Density 0.063%

    No Known Activations