© 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. 6-RES-JB
    11. 1493
    Prev
    Next
    INDEX
    Explanations

    instances where someone contacts or is contacted by another person or entity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "contacted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    puff
    -0.71
    reci
    -0.66
    bur
    -0.66
    acre
    -0.65
    scar
    -0.64
    cakes
    -0.64
    fall
    -0.63
    ffe
    -0.63
     emphasis
    -0.63
    bow
    -0.62
    POSITIVE LOGITS
    ADRA
    0.83
    govtrack
    0.76
     him
    0.75
     SOS
    0.73
     acquaintances
    0.73
    awei
    0.70
     superiors
    0.69
     Leica
    0.69
    aceae
    0.68
     reporters
    0.68
    Activations Density 0.050%

    No Known Activations