© 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. 11-RES-JB
    11. 15694
    Prev
    Next
    INDEX
    Explanations

    time-related expressions such as durations, specific time periods, and actions taking time to complete

    oai_token-act-pair · gpt-3.5-turbo

    durations 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
    ħĭ
    -0.70
    Ü
    -0.66
    eworld
    -0.65
    ociated
    -0.63
    edIn
    -0.62
    rored
    -0.60
    holm
    -0.59
     Trafford
    -0.58
     kindred
    -0.57
    ²
    -0.57
    POSITIVE LOGITS
     longer
    0.92
     to
    0.90
     before
    0.81
     elapsed
    0.76
     apiece
    0.75
     for
    0.71
     till
    0.69
     til
    0.67
    to
    0.66
     (~
    0.66
    Activations Density 0.075%

    No Known Activations