© 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. 6-RES-JB
    11. 23749
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, especially those ending with 'ile'

    oai_token-act-pair · gpt-3.5-turbo

    references to "ile" endings, which are commonly associated with medical or biological terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.95
    iversal
    -0.91
    icter
    -0.91
    icum
    -0.88
    olver
    -0.85
    etheless
    -0.82
    ipeg
    -0.82
    aido
    -0.82
    axter
    -0.82
    nesota
    -0.80
    POSITIVE LOGITS
    mma
    1.05
    tto
    1.01
    zza
    0.85
    ttes
    0.80
    tt
    0.78
    tsky
    0.78
    aments
    0.75
    gged
    0.73
    tta
    0.71
    vich
    0.71
    Activations Density 0.030%

    No Known Activations