© 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. 2263
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideologies and affiliations

    oai_token-act-pair · gpt-3.5-turbo

    political affiliations and terms related to conservative, liberal, and libertarian ideologies

    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
    obyl
    -0.84
    peak
    -0.79
    utics
    -0.77
    cedented
    -0.77
    models
    -0.77
    pread
    -0.74
    ptions
    -0.71
    acca
    -0.71
    ingen
    -0.70
    thia
    -0.69
    POSITIVE LOGITS
     group
    1.00
     organization
    0.98
     watchdog
    0.97
     organisation
    0.97
     nonprofit
    0.95
     enclave
    0.94
     consortium
    0.91
     alliance
    0.91
     entity
    0.90
     firm
    0.88
    Activations Density 0.229%

    No Known Activations