© 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. 4-RES-JB
    11. 22273
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, specifically durations and periods of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time, specifically durations or experiences in months and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.77
    Area
    -0.76
    JV
    -0.75
    cause
    -0.74
    quote
    -0.71
    onto
    -0.67
    Sport
    -0.66
    MpServer
    -0.65
     behav
    -0.65
     holiest
    -0.64
    POSITIVE LOGITS
     hiatus
    0.93
     stal
    0.79
     setbacks
    0.75
    hus
    0.72
    cation
    0.72
     exhausting
    0.71
     hesitation
    0.70
     separation
    0.69
    iatus
    0.68
     lapse
    0.68
    Activations Density 0.225%

    No Known Activations