© 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. 10652
    Prev
    Next
    INDEX
    Explanations

    times of the day

    oai_token-act-pair · gpt-3.5-turbo

    specific time markers or references

    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
    ahime
    -0.87
    gression
    -0.73
    enhagen
    -0.67
     Spoiler
    -0.63
    eatures
    -0.63
     Fiorina
    -0.63
     Heller
    -0.61
     Franchise
    -0.60
     Handbook
    -0.60
     Brid
    -0.59
    POSITIVE LOGITS
    clock
    1.46
    morning
    1.23
     morning
    1.23
    Clock
    1.15
     curfew
    1.07
     afternoon
    1.05
     mornings
    1.00
     evening
    0.99
     night
    0.98
     clock
    0.94
    Activations Density 0.084%

    No Known Activations