© 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. 3-RES-JB
    11. 4039
    Prev
    Next
    INDEX
    Explanations

    words related to time duration

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations, specifically the word "minute."

    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
    ashtra
    -0.89
     Consortium
    -0.75
    IGH
    -0.70
    INA
    -0.68
    liga
    -0.64
    aspers
    -0.64
     CSI
    -0.63
    fit
    -0.63
    Fit
    -0.63
    solid
    -0.63
    POSITIVE LOGITS
    aneously
    0.84
     Maid
    0.80
     livest
    0.73
    aire
    0.72
    adelphia
    0.72
    aneous
    0.72
     twitch
    0.70
    naire
    0.70
    neapolis
    0.70
    otaur
    0.69
    Activations Density 0.029%

    No Known Activations