© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 2707
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific individual named Vince McMahon

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Vince" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cknow
    -0.83
    eday
    -0.77
    NetMessage
    -0.75
    uyomi
    -0.74
    ĨĴ
    -0.73
    mares
    -0.71
    umn
    -0.71
    emis
    -0.65
    owitz
    -0.64
     Dispatch
    -0.64
    POSITIVE LOGITS
     Staples
    1.11
     McMahon
    1.09
    ption
    0.89
    utical
    0.87
    aneous
    0.83
    riors
    0.81
    mma
    0.80
    riot
    0.80
    rament
    0.78
    IELD
    0.77
    Activations Density 0.047%

    No Known Activations