© 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. 13637
    Prev
    Next
    INDEX
    Explanations

    words related to political processes and events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating political processes and legislative actions

    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
    Interstitial
    -0.83
    obyl
    -0.80
    Used
    -0.77
    iosity
    -0.74
    Favorite
    -0.72
    Really
    -0.72
    rack
    -0.72
    wow
    -0.71
    Honestly
    -0.70
    à¨
    -0.68
    POSITIVE LOGITS
     organisers
    1.12
     lawmakers
    1.11
     negotiators
    1.08
     analysts
    0.97
     officials
    0.96
     campaigners
    0.96
     observers
    0.94
     organizers
    0.93
     representatives
    0.93
     interim
    0.91
    Activations Density 0.573%

    No Known Activations