© 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. 9-RES-JB
    11. 4563
    Prev
    Next
    INDEX
    Explanations

    politically related statements or mentions of political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to political endorsements and related scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     licence
    -0.92
     licences
    -0.88
     explorers
    -0.85
     civilisation
    -0.84
     recognised
    -0.83
    sterdam
    -0.82
     recognise
    -0.77
     Whilst
    -0.76
     realise
    -0.76
     realised
    -0.73
    POSITIVE LOGITS
     Politico
    1.50
     POLITICO
    1.38
     GOP
    1.36
    Republicans
    1.32
    Democrats
    1.32
     RNC
    1.31
     Priebus
    1.31
     MSNBC
    1.31
    GOP
    1.25
    CNN
    1.25
    Activations Density 1.912%

    No Known Activations