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

    Neuronpedia

    Jacobian LensNEW
    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. 3362
    Prev
    Next
    INDEX
    Explanations

    power-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to power dynamics and influence

    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
    holiday
    -0.89
     Café
    -0.84
    çīĪ
    -0.84
     holiday
    -0.82
    aturdays
    -0.76
    dates
    -0.75
    Kids
    -0.75
    Tour
    -0.74
     café
    -0.74
    cember
    -0.73
    POSITIVE LOGITS
     wield
    1.51
     wielded
    1.50
     exerted
    1.45
     power
    1.36
     exert
    1.34
     POWER
    1.31
     powerless
    1.29
    power
    1.26
     influence
    1.25
    Power
    1.23
    Activations Density 0.453%

    No Known Activations