© 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 EvalsExportsinterp-engineNEWAPI 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. 9727
    Prev
    Next
    INDEX
    Explanations

    proper nouns associated with a particular person named Theresa May

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Theresa May" along with dates related to her activities

    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
    Seattle
    -0.83
     Honolulu
    -0.82
     Hawai
    -0.77
     Gree
    -0.75
     Chero
    -0.72
     Roku
    -0.71
     Siber
    -0.71
    Methods
    -0.71
     Grape
    -0.70
    Ô
    -0.70
    POSITIVE LOGITS
     appoint
    0.97
    agher
    0.90
     ministerial
    0.86
     ministers
    0.86
     cabinet
    0.84
     congratulated
    0.83
     urgently
    0.81
     appointed
    0.80
     criticised
    0.79
    iband
    0.78
    Activations Density 0.105%

    No Known Activations