© 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. 4-RES-JB
    6. 7087
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures with the title "Prime Minister"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political leaders, specifically Prime Ministers

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

    No Comments

    Negative Logits
    MpServer
    -0.85
     needles
    -0.70
    atha
    -0.68
    bring
    -0.66
    banks
    -0.65
    crew
    -0.63
    bleacher
    -0.63
     needle
    -0.62
    learning
    -0.62
    rights
    -0.62
    POSITIVE LOGITS
     Shinzo
    1.03
     Narendra
    0.84
     Minister
    0.81
     Theresa
    0.78
    doms
    0.77
     Ministers
    0.77
     Recep
    0.77
     Marshal
    0.76
     ministerial
    0.74
     ministers
    0.72
    Activations Density 0.030%

    No Known Activations