© 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. 4-RES-JB
    11. 543
    Prev
    Next
    INDEX
    Explanations

    phrases related to social or economic elites in society

    oai_token-act-pair · gpt-3.5-turbo

    references to social and political elites

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

    No Comments

    Negative Logits
     Archangel
    -0.73
    gain
    -0.71
    leaf
    -0.70
    TPPStreamerBot
    -0.69
    asca
    -0.68
    gger
    -0.67
    faith
    -0.67
     Dragonbound
    -0.66
    Capt
    -0.63
    inventoryQuantity
    -0.63
    POSITIVE LOGITS
     elites
    1.05
    ablishment
    1.01
    ervatives
    0.83
     Institution
    0.83
     elite
    0.82
     liberalism
    0.80
     liberals
    0.79
     circles
    0.77
    uminati
    0.77
     dict
    0.76
    Activations Density 0.037%

    No Known Activations