© 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. 17514
    Prev
    Next
    INDEX
    Explanations

    references to torrenting, file-sharing, and related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to torrenting and file-sharing

    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
    erity
    -0.79
    mberg
    -0.78
    utenant
    -0.76
    ufact
    -0.73
    uten
    -0.72
    nyder
    -0.69
     Danger
    -0.69
    inition
    -0.67
     Pigs
    -0.64
    ggle
    -0.60
    POSITIVE LOGITS
    ial
    1.47
    Fre
    0.93
    icular
    0.90
    ials
    0.86
    ious
    0.81
    icularly
    0.80
     downloads
    0.78
     torrent
    0.78
    pool
    0.76
    s
    0.75
    Activations Density 0.063%

    No Known Activations