© 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. 9-RES-JB
    11. 20860
    Prev
    Next
    INDEX
    Explanations

    dates and numerical sequences

    oai_token-act-pair · gpt-3.5-turbo

    references to time or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.94
    Materials
    -0.73
     prospects
    -0.66
    _.
    -0.62
    iatures
    -0.59
    ();
    -0.59
     EDITION
    -0.58
     Dresden
    -0.58
     prospect
    -0.58
    Product
    -0.56
    POSITIVE LOGITS
     incorrectly
    0.84
     deficient
    0.79
    interrupted
    0.78
     ERROR
    0.78
     inconsistent
    0.75
     unfit
    0.74
     unsafe
    0.74
    reverse
    0.74
     incorrect
    0.74
    perfect
    0.74
    Activations Density 1.073%

    No Known Activations