© 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. 7-RES-JB
    11. 1440
    Prev
    Next
    INDEX
    Explanations

    references to time durations, specifically years or spans of years

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time, particularly multi-year periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achus
    -0.79
     Clever
    -0.71
    alos
    -0.64
    iants
    -0.64
    paces
    -0.63
     Rooms
    -0.63
    hops
    -0.62
    icio
    -0.62
    ech
    -0.62
    urn
    -0.61
    POSITIVE LOGITS
     ago
    1.05
     anniversary
    0.99
     hiatus
    0.91
    long
    0.87
    iversary
    0.85
     itch
    0.79
     period
    0.78
     olds
    0.75
     gestation
    0.75
     lapse
    0.74
    Activations Density 0.045%

    No Known Activations