© 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 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. 10-RES-JB
    11. 3449
    Prev
    Next
    INDEX
    Explanations

    specific times and programming schedules

    oai_token-act-pair · gpt-3.5-turbo

    specific times or schedules for events

    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
     Bland
    -0.74
     Haku
    -0.74
     DES
    -0.73
     Berserker
    -0.72
     Cutter
    -0.71
     Geographic
    -0.70
     Hawkins
    -0.69
     Wra
    -0.69
     UA
    -0.67
     HS
    -0.67
    POSITIVE LOGITS
    pm
    1.92
     pm
    1.38
    am
    1.31
    noon
    1.30
    PM
    1.28
    mins
    1.19
     noon
    1.08
    morrow
    1.04
     midnight
    1.03
    km
    1.01
    Activations Density 0.033%

    No Known Activations