© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3194
    Prev
    Next
    INDEX
    Explanations

    words related to time, specifically focusing on the concept of clocks and timing

    oai_token-act-pair · gpt-3.5-turbo

    references to time, specifically related 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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rito
    -0.80
    cca
    -0.75
    Sov
    -0.70
    Priv
    -0.69
    KEN
    -0.66
     LC
    -0.64
    cer
    -0.64
    du
    -0.64
     Buc
    -0.63
    ki
    -0.63
    POSITIVE LOGITS
    clock
    1.01
    wise
    1.00
    ulhu
    0.80
    urnal
    0.79
    agascar
    0.78
    elfth
    0.77
     Clock
    0.77
    ayson
    0.74
    OWER
    0.74
    ilies
    0.71
    Activations Density 0.005%

    No Known Activations