© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12746
    Prev
    Next
    INDEX
    Explanations

    words ending in '-se'

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical measurements or counts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ONSORED
    -0.77
    MORE
    -0.73
    REDACTED
    -0.73
    HUD
    -0.67
    è£ħ
    -0.64
    WOR
    -0.63
     PUBLIC
    -0.62
     ducks
    -0.61
    Correct
    -0.60
    =-=-=-=-
    -0.59
    POSITIVE LOGITS
    enth
    0.93
    velength
    0.93
    gment
    0.91
    imester
    0.89
    itter
    0.87
    verage
    0.86
    undred
    0.85
    imensional
    0.84
    ousand
    0.83
    ibling
    0.83
    Activations Density 0.100%

    No Known Activations