© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11441
    Prev
    Next
    INDEX
    Explanations

    time-related phrases ranging from millions to billions of years ago

    oai_token-act-pair · gpt-3.5-turbo

    references to age and time periods in years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rez
    -0.64
    iqu
    -0.63
    govtrack
    -0.62
    odox
    -0.61
    ilyn
    -0.61
    WN
    -0.61
    atically
    -0.61
    aunch
    -0.61
    rano
    -0.60
    Priv
    -0.60
    POSITIVE LOGITS
     ago
    1.29
     Ago
    0.94
     old
    0.81
    osaurs
    0.81
     olds
    0.80
     BCE
    0.77
     hindsight
    0.73
    idia
    0.73
    arians
    0.71
    Ancient
    0.71
    Activations Density 0.088%

    No Known Activations