© 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. 7129
    Prev
    Next
    INDEX
    Explanations

    phrases related to being taken to a hospital for treatment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "taken" 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
    lich
    -0.71
    eers
    -0.67
    tch
    -0.64
    tions
    -0.64
    ler
    -0.64
    witz
    -0.63
    hart
    -0.63
    til
    -0.62
    psey
    -0.62
    tem
    -0.62
    POSITIVE LOGITS
     aback
    1.14
    aways
    1.00
    ãĤ¤ãĥĪ
    0.89
    OVER
    0.89
     heed
    0.81
    ãĥĥãĥĪ
    0.80
     advantage
    0.80
     away
    0.77
    overs
    0.77
    ardless
    0.76
    Activations Density 0.044%

    No Known Activations