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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 21241
    Prev
    Next
    INDEX
    Explanations

    References to the political figure "Theresa May."

    oai_token-act-pair · gpt-3.5-turbo

    references to Theresa May, the British Prime Minister

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assian
    -0.89
    asper
    -0.77
    inctions
    -0.72
    ioned
    -0.71
    venants
    -0.71
    aturation
    -0.70
    ilver
    -0.69
    vernment
    -0.69
    alach
    -0.69
    oning
    -0.68
    POSITIVE LOGITS
     Theresa
    0.79
     herself
    0.76
     Thatcher
    0.76
     Hunt
    0.70
     Merkel
    0.67
     Wynne
    0.67
     Devi
    0.67
     Sut
    0.66
     Anne
    0.66
     Clarkson
    0.63
    Activations Density 0.019%

    No Known Activations