© 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. 11-RES-JB
    11. 22655
    Prev
    Next
    INDEX
    Explanations

    mentions of government officials with the title "Secretary"

    oai_token-act-pair · gpt-3.5-turbo

    references to government officials and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aic
    -0.67
    onga
    -0.62
    anu
    -0.59
    ivia
    -0.56
    É
    -0.56
     Jungle
    -0.56
    sv
    -0.55
    MQ
    -0.54
    DX
    -0.54
    cape
    -0.54
    POSITIVE LOGITS
    general
    0.99
    General
    0.89
     Tillerson
    0.88
     General
    0.85
     Clinton
    0.83
    alse
    0.82
    assetsadobe
    0.80
     nominee
    0.78
     of
    0.78
     secretary
    0.76
    Activations Density 0.036%

    No Known Activations