© 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. 1-RES-JB
    11. 3583
    Prev
    Next
    INDEX
    Explanations

    words related to power and control, especially focusing on political and economic elites

    oai_token-act-pair · gpt-3.5-turbo

    references to social and political elites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥ³
    -0.81
     Archangel
    -0.73
    SourceFile
    -0.70
     Dull
    -0.68
     Ship
    -0.67
    agh
    -0.66
    upon
    -0.66
     Deadly
    -0.66
    Õ
    -0.66
    atur
    -0.66
    POSITIVE LOGITS
     elites
    1.19
    ervatives
    0.92
    ablishment
    0.91
    rats
    0.88
     incent
    0.88
     millenn
    0.82
    ervative
    0.81
     princ
    0.81
    usional
    0.81
     elite
    0.80
    Activations Density 0.015%

    No Known Activations