© 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. 3-RES-JB
    11. 1548
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the name "Hu"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the name "Hu."

    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
    20439
    -0.97
    */(
    -0.88
    ãĥĩãĤ£
    -0.77
    Ú
    -0.76
    ãĥ¼ãĥĨ
    -0.72
    Interstitial
    -0.72
    creen
    -0.71
    pmwiki
    -0.71
    cape
    -0.70
     Leviathan
    -0.69
    POSITIVE LOGITS
    awei
    1.33
    lda
    1.08
    anca
    1.05
     Hu
    1.03
    Hu
    0.97
    bert
    0.95
    acan
    0.94
    isine
    0.93
    enn
    0.92
    undai
    0.92
    Activations Density 0.006%

    No Known Activations