© 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. 1-RES-JB
    11. 7409
    Prev
    Next
    INDEX
    Explanations

    words related to decoration or being adorned

    oai_token-act-pair · gpt-3.5-turbo

    terms related to decoration and embellishment

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    FS
    -0.79
     FTA
    -0.75
    PU
    -0.72
    FER
    -0.70
    GH
    -0.69
    RS
    -0.69
    ffic
    -0.69
    demand
    -0.68
    appro
    -0.67
    LS
    -0.66
    POSITIVE LOGITS
     decorated
    1.39
     decoration
    1.38
     decorations
    1.38
     decor
    1.05
    nesday
    0.90
    ocument
    0.89
    rette
    0.83
    dinand
    0.83
     colours
    0.82
    issance
    0.81
    Activations Density 0.006%

    No Known Activations