© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15366
    Prev
    Next
    INDEX
    Explanations

    adjectives describing extravagance or complexity

    oai_token-act-pair · gpt-3.5-turbo

    descriptors that signify complexity, extravagance, and opulence

    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
    ppo
    -0.80
    lean
    -0.80
    bern
    -0.78
    utenant
    -0.78
    gage
    -0.77
    eper
    -0.73
    ighed
    -0.72
    Lean
    -0.69
    cknow
    -0.69
    ander
    -0.69
    POSITIVE LOGITS
    ly
    0.86
    ulously
    0.82
     mish
    0.76
     rendition
    0.74
     stunts
    0.71
     antics
    0.71
     conspiracy
    0.70
     recre
    0.70
     schemes
    0.70
     plot
    0.68
    Activations Density 0.035%

    No Known Activations