© 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. 10-RES-JB
    11. 18529
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a person's name, likely "Lu."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lu"

    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
    âĶģ
    -0.72
     Skydragon
    -0.69
    raints
    -0.67
     Junction
    -0.67
     Compass
    -0.65
    ledged
    -0.64
     Oath
    -0.63
    stretched
    -0.62
    ij士
    -0.62
     backdrop
    -0.62
    POSITIVE LOGITS
    igi
    1.29
    pton
    1.16
    cci
    1.15
    cius
    1.09
    cca
    1.07
    ppa
    1.02
    ongo
    1.02
    zon
    0.98
    ci
    0.98
    zac
    0.96
    Activations Density 0.020%

    No Known Activations