Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7494
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Torrent"

    oai_token-act-pair · gpt-3.5-turbo

    references to BitTorrent and related file-sharing concepts

    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
     Ze
    -0.62
     objective
    -0.62
     special
    -0.61
     base
    -0.60
     equ
    -0.60
     whether
    -0.60
     GI
    -0.59
     AF
    -0.59
     AB
    -0.59
     allied
    -0.59
    POSITIVE LOGITS
    Torrent
    3.77
     torrent
    2.16
    VPN
    1.39
     Torrent
    1.15
    Shares
    1.12
    DVD
    1.12
    Magikarp
    1.11
    pload
    1.03
    Stream
    1.02
    Netflix
    1.01
    Activations Density 0.012%

    No Known Activations