© 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. 22423
    Prev
    Next
    INDEX
    Explanations

    phrases related to government positions, specifically the position of secretary

    oai_token-act-pair · gpt-3.5-turbo

    references to government positions and 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
     Fault
    -1.12
     Coverage
    -1.11
     Piece
    -1.11
     Spread
    -1.10
     Eff
    -1.09
     Shed
    -1.09
     Years
    -1.09
     Label
    -1.09
     Tight
    -1.08
     Chains
    -1.08
    POSITIVE LOGITS
     chancellor
    1.09
     treasurer
    1.05
     senate
    1.01
     arts
    1.01
     general
    0.98
     sciences
    0.96
     commons
    0.96
     prince
    0.94
     secretary
    0.94
     commerce
    0.94
    Activations Density 0.415%

    No Known Activations