© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 23360
    Prev
    Next
    INDEX
    Explanations

    the name "Billy" as a strong match, especially when it is used in various contexts and forms

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Billy or Farrell

    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
    ional
    -0.86
    yrinth
    -0.83
    igating
    -0.82
    arin
    -0.80
    ATIONAL
    -0.79
    perse
    -0.74
    igation
    -0.73
    igators
    -0.73
    igated
    -0.73
    egal
    -0.72
    POSITIVE LOGITS
     Joel
    0.90
     Billy
    0.85
     Graham
    0.85
    Billy
    0.85
    cock
    0.83
    cakes
    0.77
     Pilgrim
    0.77
    cats
    0.75
    istries
    0.75
     Murphy
    0.74
    Activations Density 0.010%

    No Known Activations