© 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. 4-RES-JB
    11. 1416
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "the" preceded by a specific number

    oai_token-act-pair · gpt-3.5-turbo

    consistent mentions of the word "the."

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

    No Comments

    Negative Logits
    arten
    -0.72
    etsk
    -0.70
    illion
    -0.67
    arella
    -0.67
    elaide
    -0.65
     besides
    -0.64
    ãĤ´ãĥ³
    -0.64
    ova
    -0.63
    hari
    -0.63
    ÃĥÃĤ
    -0.63
    POSITIVE LOGITS
     aforementioned
    1.15
     latter
    1.08
     entire
    1.00
     utmost
    0.98
     smallest
    0.95
     same
    0.93
     impending
    0.92
     slightest
    0.88
     sexes
    0.85
     dreaded
    0.84
    Activations Density 0.378%

    No Known Activations