© 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. 9-RES-JB
    11. 18203
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific publication, in this case, "The New York Times."

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "The" in various contexts within the document

    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
    ionics
    -0.81
    ensis
    -0.79
    shoot
    -0.74
    perse
    -0.73
    -----------
    -0.73
    uphem
    -0.73
    hang
    -0.71
    oubted
    -0.70
    itures
    -0.68
    ilings
    -0.66
    POSITIVE LOGITS
    atre
    0.86
    odor
    0.86
     Huffington
    0.84
     Verge
    0.84
     Associated
    0.77
     Hague
    0.77
     Netherlands
    0.75
    resa
    0.73
    oret
    0.72
     Daily
    0.71
    Activations Density 0.024%

    No Known Activations