© 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. 2308
    Prev
    Next
    INDEX
    Explanations

    dates of birth

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Born"

    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
    olson
    -0.67
    ĵĺ
    -0.66
    phas
    -0.66
    awaru
    -0.65
    iqu
    -0.63
    acea
    -0.63
    awatts
    -0.62
    tools
    -0.62
    arty
    -0.62
    Apps
    -0.61
    POSITIVE LOGITS
     Sidney
    0.90
     Dorothy
    0.90
     April
    0.89
     Milton
    0.86
     Jan
    0.85
     August
    0.84
     Oct
    0.84
     June
    0.84
     Robert
    0.82
     Samuel
    0.82
    Activations Density 0.023%

    No Known Activations