© 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
    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. 7806
    Prev
    Next
    INDEX
    Explanations

    governmental entities or authorities

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental and institutional entities or actions

    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
     wrinkles
    -0.76
     bets
    -0.72
    latable
    -0.67
    pleted
    -0.64
    pread
    -0.64
    phies
    -0.63
    rosso
    -0.63
    ãĥĻ
    -0.62
    stood
    -0.62
    prototype
    -0.62
    POSITIVE LOGITS
     authorities
    1.26
     administration
    1.08
     bureaucracy
    1.07
     legislature
    1.06
     judiciary
    1.06
     government
    1.02
     regulator
    0.99
     Directorate
    0.99
     Legislature
    0.97
     Ministry
    0.97
    Activations Density 0.345%

    No Known Activations