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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12327
    Prev
    Next
    INDEX
    Explanations

    terms related to martial arts

    oai_token-act-pair · gpt-3.5-turbo

    references to mixed martial arts and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.82
    */(
    -0.80
    greSQL
    -0.78
    iday
    -0.76
    PsyNetMessage
    -0.75
     UID
    -0.75
    caps
    -0.74
    istors
    -0.72
    blank
    -0.72
    uter
    -0.71
    POSITIVE LOGITS
     arts
    1.31
     martial
    1.04
     practitioners
    1.04
     Arts
    0.98
    itsu
    0.97
     Fighting
    0.95
     Jiu
    0.94
     practitioner
    0.93
     Kung
    0.93
    fighting
    0.91
    Activations Density 0.055%

    No Known Activations