© 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. 10-RES-JB
    11. 3259
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "China"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "China"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Payton
    -0.80
     Hitchcock
    -0.77
    schild
    -0.75
    numbered
    -0.74
    fitting
    -0.74
    rah
    -0.71
     Desmond
    -0.71
    iotic
    -0.70
     Ajax
    -0.69
    leck
    -0.69
    POSITIVE LOGITS
     Jinping
    1.25
     Yuan
    1.21
     yuan
    1.13
     Xin
    1.10
     Zhu
    1.09
     Jing
    1.05
     Unic
    1.01
     Tai
    1.01
     Guang
    0.98
     Tian
    0.95
    Activations Density 0.060%

    No Known Activations