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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 2603
    Prev
    Next
    INDEX
    Explanations

    words related to file sharing and online file transfer services

    oai_token-act-pair · gpt-3.5-turbo

    references to torrenting and file-sharing platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    herty
    -0.74
    br
    -0.73
    ignment
    -0.69
    igning
    -0.68
    pt
    -0.67
     Continental
    -0.66
    hr
    -0.66
    IPS
    -0.63
     ble
    -0.61
     void
    -0.61
    POSITIVE LOGITS
    Torrent
    1.15
    ographers
    0.85
     Torrent
    0.81
    Maps
    0.79
    Client
    0.76
     Slave
    0.74
    Fre
    0.74
     Browser
    0.73
     Unlimited
    0.73
    DragonMagazine
    0.73
    Activations Density 0.022%

    No Known Activations