© 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. 0-RES-JB
    11. 21782
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Elaine."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "aine"

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

    No Comments

    Negative Logits
     tapping
    -0.73
     tables
    -0.64
     Social
    -0.64
     subscribed
    -0.62
     rounded
    -0.61
     collections
    -0.60
     spaghetti
    -0.60
     Tot
    -0.60
    )=(
    -0.59
     RSS
    -0.59
    POSITIVE LOGITS
    aine
    4.80
    ain
    1.80
    ayne
    1.77
    raine
    1.45
    ane
    1.27
    ains
    1.27
    AIN
    1.12
    agne
    1.10
    aint
    1.09
    aign
    1.01
    Activations Density 0.015%

    No Known Activations