© 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. 6623
    Prev
    Next
    INDEX
    Explanations

    specific years or date ranges mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of years and numeric data related to time

    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
     Beir
    -0.66
    onga
    -0.66
     Hog
    -0.65
     Bard
    -0.62
     Anthem
    -0.60
    ARM
    -0.59
     1840
    -0.59
     Hamilton
    -0.59
    icons
    -0.57
     toast
    -0.57
    POSITIVE LOGITS
    1999
    1.54
     1999
    1.54
    1998
    1.54
     1998
    1.50
    1996
    1.48
     1997
    1.45
     1996
    1.45
    1997
    1.44
     1995
    1.44
    1995
    1.44
    Activations Density 0.065%

    No Known Activations