© 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. 9-RES-JB
    11. 15570
    Prev
    Next
    INDEX
    Explanations

    phrases related to martial arts

    oai_token-act-pair · gpt-3.5-turbo

    references to martial arts terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istors
    -0.78
    greSQL
    -0.74
    itant
    -0.73
    uter
    -0.72
    iday
    -0.72
    ibel
    -0.72
    ļéĨĴ
    -0.70
    qv
    -0.69
    */(
    -0.68
    bos
    -0.68
    POSITIVE LOGITS
     arts
    1.22
     practitioners
    0.91
     Arts
    0.90
    fighting
    0.87
     martial
    0.84
     prowess
    0.84
     chops
    0.82
    fighter
    0.81
    itsu
    0.80
     spar
    0.79
    Activations Density 0.073%

    No Known Activations