© 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. 20410
    Prev
    Next
    INDEX
    Explanations

    phrases indicating dedication or commitment to a cause

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "devoted."

    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
     Ain
    -0.73
     Solomon
    -0.72
     Jacob
    -0.68
     Fargo
    -0.67
     Kessler
    -0.66
     Frankenstein
    -0.66
     Faust
    -0.65
    ocker
    -0.65
    CHA
    -0.65
     Browne
    -0.65
    POSITIVE LOGITS
     devoted
    1.28
     devote
    1.04
    itures
    0.92
    entious
    0.89
     citiz
    0.89
    yssey
    0.87
    mable
    0.84
    vier
    0.82
    icion
    0.82
    secut
    0.81
    Activations Density 0.008%

    No Known Activations