© 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. 10-RES-JB
    11. 18925
    Prev
    Next
    INDEX
    Explanations

    verbs related to specific timeframes, particularly the word "today."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days or times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uploads
    -0.71
    paralle
    -0.71
    ettle
    -0.71
    pires
    -0.69
     Journals
    -0.68
     Ammunition
    -0.67
    rar
    -0.65
    eers
    -0.65
    VK
    -0.62
    obos
    -0.62
    POSITIVE LOGITS
     afternoon
    1.26
     morning
    1.26
     evening
    1.18
    morning
    1.01
     night
    1.00
     mornings
    0.91
    night
    0.89
     viz
    0.81
     evenings
    0.78
     Evening
    0.77
    Activations Density 0.161%

    No Known Activations