© 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. 23316
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find instances of the word "flip" with varying contexts and subjects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "flip" and its variations in a variety of contexts

    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
    lain
    -0.76
    FORE
    -0.74
    ridor
    -0.69
     Annotations
    -0.69
    Interstitial
    -0.67
     pains
    -0.67
    mble
    -0.66
    CLA
    -0.65
    hart
    -0.64
    aph
    -0.63
    POSITIVE LOGITS
    olitics
    1.05
     burgers
    0.90
     flipped
    0.88
     flips
    0.83
    tera
    0.82
     flo
    0.81
    ety
    0.80
    switch
    0.79
    erenn
    0.77
     flipping
    0.76
    Activations Density 0.036%

    No Known Activations