© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11-RES-JB
    11. 12833
    Prev
    Next
    INDEX
    Explanations

    superlatives such as "largest," "oldest," "tallest," and "fastest."

    oai_token-act-pair · gpt-3.5-turbo

    superlatives and rankings of various entities or achievements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    rils
    -0.99
    ravings
    -0.91
    ãĤ¦ãĤ¹
    -0.91
    IGHTS
    -0.88
    idges
    -0.87
    ashes
    -0.85
    acements
    -0.84
    antics
    -0.83
    aucuses
    -0.82
    adders
    -0.82
    POSITIVE LOGITS
     extant
    1.01
     ever
    1.00
     piece
    0.97
     continuously
    0.95
     privately
    0.91
     standalone
    0.90
     single
    0.88
     entity
    0.88
     employer
    0.87
     thing
    0.85
    Activations Density 0.152%

    No Known Activations