© 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. 3497
    Prev
    Next
    INDEX
    Explanations

    words related to embarking or going on a journey

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a journey

    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
    essee
    -0.76
    uctor
    -0.70
    uppet
    -0.67
     topical
    -0.67
    missive
    -0.66
     glove
    -0.65
    ividual
    -0.64
    inki
    -0.64
    ogun
    -0.64
    idency
    -0.64
    POSITIVE LOGITS
     Journey
    0.99
     journey
    0.99
     journeys
    0.97
     voyage
    0.94
    naire
    0.90
    wright
    0.86
    è£ħ
    0.85
     Explorer
    0.83
    icular
    0.82
    yssey
    0.81
    Activations Density 0.012%

    No Known Activations