© 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. 0-RES-JB
    11. 2035
    Prev
    Next
    INDEX
    Explanations

    terms related to online piracy

    oai_token-act-pair · gpt-3.5-turbo

    terminology and references related to piracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ely
    -0.87
     DOE
    -0.79
     Kell
    -0.77
    Michelle
    -0.74
     Heidi
    -0.72
     Goff
    -0.72
    Denver
    -0.71
     Shelter
    -0.70
     Weber
    -0.69
     Ket
    -0.68
    POSITIVE LOGITS
     piracy
    3.64
     pirates
    3.43
     pirate
    2.98
     pir
    2.88
    Pir
    2.61
     Pir
    2.26
     Pirates
    2.25
    piracy
    1.74
     Pirate
    1.70
     DRM
    1.40
    Activations Density 0.022%

    No Known Activations