© 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. 2-RES-JB
    11. 12639
    Prev
    Next
    INDEX
    Explanations

    political figures, actions, and events

    oai_token-act-pair · gpt-3.5-turbo

    references to political actions and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginners
    -0.77
    utic
    -0.74
     endeavour
    -0.74
     realised
    -0.72
     fulfil
    -0.70
     regeneration
    -0.70
     arte
    -0.69
    ptin
    -0.67
     metre
    -0.65
     brill
    -0.65
    POSITIVE LOGITS
    Republicans
    1.11
    Democrats
    1.10
     Republican
    1.09
    Republican
    1.09
     Democrat
    1.04
    President
    1.03
     bipartisan
    1.02
     Libertarian
    1.01
     Politico
    1.01
     GOP
    1.00
    Activations Density 3.260%

    No Known Activations