© 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. 11-RES-JB
    11. 9436
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a duration of time, specifically "for some time" and "quite some time"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that repeatedly mention the duration of time

    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
    ibel
    -0.70
    âĨij
    -0.63
    velt
    -0.61
    eki
    -0.60
    ned
    -0.60
    Js
    -0.58
    acus
    -0.57
    ible
    -0.56
     Caption
    -0.56
     Converted
    -0.56
    POSITIVE LOGITS
     time
    1.63
    years
    1.33
     years
    1.33
    months
    1.25
    time
    1.24
     months
    1.24
     periods
    1.14
     weeks
    1.13
     period
    1.10
     duration
    1.07
    Activations Density 0.091%

    No Known Activations