© 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. 10646
    Prev
    Next
    INDEX
    Explanations

    references to time durations in years

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time, specifically the term "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
    hod
    -0.75
    amina
    -0.73
    ople
    -0.72
    iqu
    -0.72
     Tray
    -0.71
    icc
    -0.68
    apa
    -0.62
     Shack
    -0.61
    anamo
    -0.60
     contag
    -0.59
    POSITIVE LOGITS
     ago
    1.28
     Ago
    1.01
     olds
    0.85
     anniversary
    0.81
     consecut
    0.79
    long
    0.78
    ÙĨ
    0.70
    åħī
    0.70
    姫
    0.69
    iott
    0.67
    Activations Density 0.080%

    No Known Activations