© 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. 10-RES-JB
    11. 10621
    Prev
    Next
    INDEX
    Explanations

    terms related to illegal file sharing and copyright infringement

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to copyright issues and digital content piracy

    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
    helle
    -0.89
    aukee
    -0.85
    anship
    -0.84
     Prescott
    -0.83
    rition
    -0.82
    ointment
    -0.80
    isSpecialOrderable
    -0.79
    ãĤ©
    -0.79
    HUD
    -0.78
    asket
    -0.76
    POSITIVE LOGITS
     DMCA
    2.02
     piracy
    1.91
     copyright
    1.84
    Torrent
    1.75
     pir
    1.63
     DRM
    1.61
     infringing
    1.60
     Torrent
    1.58
     downloading
    1.55
     censorship
    1.53
    Activations Density 0.419%

    No Known Activations