© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1523
    Prev
    Next
    INDEX
    Explanations

    words related to political leaders with the title of "Chancellor."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political leaders, specifically chancellors

    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
    cart
    -0.75
     brush
    -0.75
     tet
    -0.62
    gas
    -0.62
    IV
    -0.60
    cas
    -0.60
     underwater
    -0.60
    ript
    -0.60
    ranch
    -0.60
     paddle
    -0.60
    POSITIVE LOGITS
     Chancellor
    4.13
     chancellor
    3.51
    llor
    2.13
    Chance
    2.01
     Treasurer
    1.53
     Merkel
    1.51
     Minister
    1.27
     Chamberlain
    1.21
     Speaker
    1.20
     Duchess
    1.18
    Activations Density 0.016%

    No Known Activations