© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2858
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to clocks and timekeeping

    oai_token-act-pair · gpt-3.5-turbo

    references to clocks and timekeeping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -1.05
    Reviewer
    -0.69
    itably
    -0.68
    geon
    -0.67
    ean
    -0.66
    qua
    -0.65
    iyah
    -0.64
     Marketable
    -0.64
     ACL
    -0.62
     Hodg
    -0.62
    POSITIVE LOGITS
    wise
    1.33
    work
    1.24
     ticking
    1.19
    tower
    1.12
    clock
    0.99
     ticks
    0.89
     tower
    0.88
     counting
    0.85
     Clock
    0.84
     clock
    0.81
    Activations Density 0.060%

    No Known Activations