© 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. 10-RES-JB
    11. 10734
    Prev
    Next
    INDEX
    Explanations

    mentions and titles of government officials, particularly those holding ministerial positions

    oai_token-act-pair · gpt-3.5-turbo

    references to government ministers and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     torch
    -0.65
     theaters
    -0.64
     Samurai
    -0.63
     Fighter
    -0.62
    vent
    -0.60
     theater
    -0.60
     Savior
    -0.59
     WAR
    -0.57
     rendition
    -0.57
     bladder
    -0.56
    POSITIVE LOGITS
    ial
    1.32
    arians
    1.06
    arian
    1.05
    ials
    1.00
    ially
    0.97
    onse
    0.90
    icka
    0.86
    iate
    0.81
    isms
    0.80
    ery
    0.79
    Activations Density 0.030%

    No Known Activations