© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 5043
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal structures and power dynamics

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to systemic power dynamics and state mechanisms of control

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    é¾įåĸļ士
    -0.93
    uberty
    -0.83
    heast
    -0.77
    Ļ½
    -0.74
    ELL
    -0.73
    çīĪ
    -0.72
    ricane
    -0.72
    ricanes
    -0.72
    affe
    -0.71
    recent
    -0.71
    POSITIVE LOGITS
     tyranny
    1.45
     tyrann
    1.42
     bureaucrats
    1.36
     dictatorship
    1.33
     bureaucracy
    1.33
     bureaucr
    1.32
     aristocracy
    1.30
     patronage
    1.28
     coercive
    1.25
     totalitarian
    1.25
    Activations Density 0.591%

    No Known Activations