© 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. 0-RES-JB
    11. 18854
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name "McMahan"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the name "McM" and its variations

    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
     sting
    -0.80
    agent
    -0.67
    bt
    -0.67
     poison
    -0.66
    lining
    -0.65
     silk
    -0.63
    ache
    -0.62
     ser
    -0.62
    tic
    -0.61
     bind
    -0.61
    POSITIVE LOGITS
     McM
    4.17
    Mc
    1.60
     McG
    1.47
     McGr
    1.44
     McD
    1.40
     McK
    1.35
     McInt
    1.32
     McKay
    1.32
     McL
    1.27
     McN
    1.27
    Activations Density 0.010%

    No Known Activations