© 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. 3-RES-JB
    11. 17264
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Fish"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Fish" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     clipboard
    -0.67
    iaries
    -0.66
    iary
    -0.61
     KKK
    -0.61
    lain
    -0.61
    iating
    -0.61
    isters
    -0.61
     transformer
    -0.60
     manufactured
    -0.60
     CPC
    -0.59
    POSITIVE LOGITS
    bowl
    1.01
     Fish
    0.96
    tails
    0.93
    Fish
    0.92
    adelphia
    0.91
    meat
    0.89
    tail
    0.87
    EStream
    0.86
    idon
    0.86
    brate
    0.83
    Activations Density 0.010%

    No Known Activations