© 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. 8-RES-JB
    11. 2099
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to political ruling parties

    oai_token-act-pair · gpt-3.5-turbo

    references to ruling political parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -0.89
    lished
    -0.79
    maxwell
    -0.75
    ourcing
    -0.74
    rypt
    -0.73
    aged
    -0.73
    ihar
    -0.70
    ilation
    -0.69
    asers
    -0.69
    hooting
    -0.67
    POSITIVE LOGITS
     party
    0.90
     coalition
    0.89
     bloc
    0.89
     apparatus
    0.85
     elites
    0.80
     parties
    0.77
     caste
    0.76
     ideology
    0.76
    doms
    0.74
     elite
    0.73
    Activations Density 0.029%

    No Known Activations