© 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. 0-RES-JB
    11. 13025
    Prev
    Next
    INDEX
    Explanations

    words related to bitterness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bitter" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Perform
    -0.82
     Surveillance
    -0.75
    Items
    -0.72
    Track
    -0.71
     Performance
    -0.71
    Speed
    -0.70
    anium
    -0.69
    psc
    -0.68
     scans
    -0.68
    opl
    -0.67
    POSITIVE LOGITS
     bitter
    3.53
     bitterness
    2.53
     bitterly
    1.72
     bitters
    1.59
    terness
    1.51
     sour
    1.48
     salty
    1.39
     harsh
    1.31
     vitri
    1.31
     vehement
    1.26
    Activations Density 0.020%

    No Known Activations