© 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. 13585
    Prev
    Next
    INDEX
    Explanations

    the name "Kane"

    oai_token-act-pair · gpt-3.5-turbo

    references to the player Kane

    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
     stem
    -0.77
    err
    -0.74
     SY
    -0.70
     Tunis
    -0.68
     tolerant
    -0.67
    ugs
    -0.66
     surf
    -0.65
    req
    -0.64
    round
    -0.63
    Syrian
    -0.63
    POSITIVE LOGITS
     Kane
    4.04
     Keane
    1.36
     Dane
    1.31
     Lana
    1.15
     Burke
    1.14
     Crowley
    1.14
     Blackhawks
    1.11
     Bane
    1.09
     Poc
    1.09
     Doyle
    1.08
    Activations Density 0.021%

    No Known Activations