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

    Neuronpedia

    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. 4-RES-JB
    11. 19706
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names ending in 'ker'

    oai_token-act-pair · gpt-3.5-turbo

    words that contain the suffix "ker."

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

    No Comments

    Negative Logits
    UME
    -0.79
     Cind
    -0.72
    IRD
    -0.65
    ancies
    -0.65
    UE
    -0.65
    hens
    -0.65
    erest
    -0.64
    ARY
    -0.64
    ental
    -0.64
    ERROR
    -0.62
    POSITIVE LOGITS
    chief
    1.12
    ker
    1.04
    lund
    0.91
    holm
    0.87
    pedia
    0.85
    icker
    0.84
    luster
    0.83
    haw
    0.83
    king
    0.82
    lar
    0.82
    Activations Density 0.012%

    No Known Activations