© 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. 3-RES-JB
    11. 17770
    Prev
    Next
    INDEX
    Explanations

    names, particularly the name "Katrina"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ococ
    -0.80
    gey
    -0.79
    haps
    -0.79
    assic
    -0.78
    ativity
    -0.78
     externalToEVAOnly
    -0.77
     guiActiveUn
    -0.76
    umbn
    -0.76
    nance
    -0.74
    erville
    -0.73
    POSITIVE LOGITS
    eed
    0.74
    4000
    0.74
    Demand
    0.71
    lihood
    0.70
     9000
    0.69
    jamin
    0.67
    shore
    0.66
     Prescott
    0.65
     Kuala
    0.65
    _____
    0.63
    Activations Density 0.019%

    No Known Activations