© 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. 0-RES-JB
    11. 5335
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or entities serving as a representative

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of representatives in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yss
    -0.68
    }{
    -0.66
     holes
    -0.66
    Bec
    -0.65
     ADD
    -0.62
     ropes
    -0.62
    unia
    -0.61
    oft
    -0.59
    wal
    -0.59
    eton
    -0.59
    POSITIVE LOGITS
     representative
    3.83
     representatives
    2.40
     Representative
    2.27
    represent
    1.95
     Representatives
    1.85
    Represent
    1.77
     spokesperson
    1.60
     representation
    1.48
     spokesman
    1.27
     reps
    1.27
    Activations Density 0.009%

    No Known Activations