© 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. 11-RES-JB
    11. 3411
    Prev
    Next
    INDEX
    Explanations

    specific times and dates

    oai_token-act-pair · gpt-3.5-turbo

    times and dates associated with events or deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autobi
    -0.68
     instincts
    -0.68
     cannabin
    -0.68
     imitation
    -0.67
     memoir
    -0.62
     Swanson
    -0.60
     cellul
    -0.60
     resemb
    -0.59
     grop
    -0.57
     envision
    -0.57
    POSITIVE LOGITS
     PST
    1.15
     PDT
    1.15
    UTC
    1.14
    GMT
    1.05
     CET
    1.04
     UTC
    0.98
     Ends
    0.98
     midnight
    0.98
    aturday
    0.97
     Midnight
    0.95
    Activations Density 0.318%

    No Known Activations