© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 23415
    Prev
    Next
    INDEX
    Explanations

    phrases related to file sharing, specifically mentioning the term "BitTorrent" and "MegaUpload"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to file-sharing applications, particularly focusing on BitTorrent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    br
    -0.73
    ignment
    -0.72
    igning
    -0.71
    pt
    -0.68
     intest
    -0.67
    ocrin
    -0.67
    onut
    -0.64
    gling
    -0.63
    IPS
    -0.62
    hr
    -0.62
    POSITIVE LOGITS
    Torrent
    1.26
     Downloads
    0.85
     Torrent
    0.83
     Protocol
    0.76
     Mafia
    0.74
    Maps
    0.74
    fen
    0.73
    Client
    0.72
     downloads
    0.72
    maps
    0.70
    Activations Density 0.016%

    No Known Activations