© 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. 1285
    Prev
    Next
    INDEX
    Explanations

    instances of phrases related to the concept of time spent on activities

    oai_token-act-pair · gpt-3.5-turbo

    references to the amount of time spent on various activities

    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
    ocrats
    -0.67
    eneg
    -0.65
    brids
    -0.64
    endants
    -0.63
    Ń·
    -0.63
    AAAA
    -0.63
    geries
    -0.63
    saf
    -0.62
     supra
    -0.62
    offer
    -0.61
    POSITIVE LOGITS
     time
    1.74
    time
    1.34
     TIME
    1.28
     Time
    1.21
    Time
    1.07
     downtime
    0.98
     space
    0.91
     attention
    0.87
     leisure
    0.86
     effort
    0.86
    Activations Density 0.160%

    No Known Activations