© 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. 1-RES-JB
    11. 14387
    Prev
    Next
    INDEX
    Explanations

    unrelated words containing the substring "Power"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Power" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    romeda
    -0.75
    olson
    -0.75
     Debor
    -0.74
    oslov
    -0.73
     Von
    -0.69
    00200000
    -0.68
    ean
    -0.67
     Niet
    -0.67
    Ń·
    -0.67
    ALK
    -0.66
    POSITIVE LOGITS
    Power
    0.91
     Power
    0.89
     outage
    0.85
    power
    0.84
    utonium
    0.81
    ups
    0.78
    wall
    0.77
    facts
    0.77
     cords
    0.77
    houses
    0.76
    Activations Density 0.007%

    No Known Activations