© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 7347
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Villanova" in the text

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Vill."

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

    No Comments

    Negative Logits
    manship
    -0.73
    çķ
    -0.70
     Pax
    -0.69
     chained
    -0.66
    uyomi
    -0.65
    gency
    -0.62
     pelvic
    -0.62
    umbn
    -0.62
    à¥
    -0.61
    ा
    -0.60
    POSITIVE LOGITS
    anova
    1.32
    agers
    1.19
    iage
    1.19
    ains
    1.03
    ain
    1.00
    Vill
    0.95
    oso
    0.93
    ager
    0.90
    enge
    0.86
     Vill
    0.86
    Activations Density 0.009%

    No Known Activations