© 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. 20692
    Prev
    Next
    INDEX
    Explanations

    proper names of people

    oai_token-act-pair · gpt-3.5-turbo

    capitalized names and titles, particularly 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 @ 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
     stewards
    -0.77
    igators
    -0.77
    ¥ŀ
    -0.74
    acebook
    -0.74
     surv
    -0.73
    ibaba
    -0.73
    ntil
    -0.72
    igator
    -0.70
     consum
    -0.69
    jri
    -0.68
    POSITIVE LOGITS
     Roberts
    1.06
     Michaels
    0.95
     Robinson
    0.94
     McKay
    0.93
     Kelley
    0.91
     Christensen
    0.90
     Murphy
    0.89
     Jenkins
    0.88
     Hoffman
    0.88
     Kramer
    0.87
    Activations Density 0.236%

    No Known Activations