© 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 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. 3-RES-JB
    11. 12232
    Prev
    Next
    INDEX
    Explanations

    the action of staring

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "stare" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.71
    inventoryQuantity
    -0.71
    cham
    -0.67
    mber
    -0.65
    rosse
    -0.65
    une
    -0.64
    eded
    -0.63
    classified
    -0.62
    intestinal
    -0.62
    cel
    -0.61
    POSITIVE LOGITS
     stare
    1.01
     staring
    1.00
     stares
    0.97
    creen
    0.90
     dag
    0.90
     nodd
    0.83
     stared
    0.80
     gaze
    0.80
     gazing
    0.76
    «
    0.73
    Activations Density 0.007%

    No Known Activations