Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8254
    Prev
    Next
    INDEX
    Explanations

    terms related to martial arts

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with martial arts training and techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.96
    ESA
    -0.89
    HCR
    -0.86
    âĹ¼
    -0.84
    PsyNetMessage
    -0.84
    umenthal
    -0.81
     iCloud
    -0.79
    ilight
    -0.76
    pard
    -0.75
    Bloom
    -0.75
    POSITIVE LOGITS
     martial
    1.76
     Jiu
    1.70
     Martial
    1.61
     Kung
    1.52
    ryu
    1.49
     Okin
    1.48
     MMA
    1.42
     spar
    1.30
    itsu
    1.26
     Ryu
    1.26
    Activations Density 0.149%

    No Known Activations