© 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. 21030
    Prev
    Next
    INDEX
    Explanations

    dates and times in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    dates and timestamps connected with events or tournaments

    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
     Solomon
    -0.67
     Heavenly
    -0.66
     Chamberlain
    -0.65
     literacy
    -0.65
     Sinai
    -0.63
    lier
    -0.63
     pressuring
    -0.63
    nesium
    -0.62
    iates
    -0.62
     Leth
    -0.62
    POSITIVE LOGITS
    03
    1.91
    04
    1.89
    05
    1.87
    02
    1.86
    06
    1.78
     03
    1.76
     02
    1.75
     05
    1.75
     04
    1.73
    07
    1.68
    Activations Density 0.045%

    No Known Activations