© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4339
    Prev
    Next
    INDEX
    Explanations

    the name "Gail"

    oai_token-act-pair · gpt-3.5-turbo

    the term "ail," indicating references to health issues or ailments

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    hered
    -0.70
    opausal
    -0.68
     XD
    -0.61
    aido
    -0.61
     ster
    -0.59
    itamin
    -0.59
     Haram
    -0.59
     CES
    -0.58
    rd
    -0.56
     WHO
    -0.56
    POSITIVE LOGITS
    ail
    0.91
    runner
    0.84
    ails
    0.78
    Runner
    0.77
    abe
    0.72
    ily
    0.71
    anguage
    0.70
    le
    0.70
    hoe
    0.70
    aba
    0.69
    Activations Density 0.009%

    No Known Activations