© 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. 10-RES-JB
    11. 11021
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Pirate Bay"

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to piracy and piracy culture

    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
    nyder
    -0.85
    uate
    -0.84
    mble
    -0.83
    eger
    -0.80
     Beir
    -0.79
    uates
    -0.72
    itably
    -0.72
    mberg
    -0.72
    uated
    -0.71
    ellar
    -0.71
    POSITIVE LOGITS
    Pir
    1.06
     pirates
    0.93
    cean
    0.80
     Pirate
    0.79
     piracy
    0.78
     pirate
    0.76
     Pirates
    0.76
     squid
    0.74
     ship
    0.73
     Luffy
    0.73
    Activations Density 0.036%

    No Known Activations