© 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. 2-RES-JB
    11. 643
    Prev
    Next
    INDEX
    Explanations

    the proper noun "Cuomo"

    oai_token-act-pair · gpt-4-turbo

    mentions of a specific person, Andrew Cuomo

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Andrew Cuomo

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.74
    reading
    -0.74
    WARD
    -0.73
    fully
    -0.69
    wagen
    -0.69
     Seeking
    -0.69
     Hiroshima
    -0.67
    most
    -0.65
    angular
    -0.64
    lihood
    -0.64
    POSITIVE LOGITS
     Cuomo
    1.40
    Cu
    0.89
     vetoed
    0.84
    cair
    0.82
    uliffe
    0.79
     shenan
    0.76
    isine
    0.69
    ascus
    0.66
    ukong
    0.66
     Mellon
    0.66
    Activations Density 0.004%

    No Known Activations