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. 1-RES-JB
    6. 5997
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Commons" in a legislative or parliamentary context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Commons," likely referring to parliamentary discussions or committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stal
    -0.67
    akeru
    -0.65
    istics
    -0.63
    oslav
    -0.62
     Nazi
    -0.62
    ography
    -0.61
     Shinji
    -0.61
    ographies
    -0.61
    ihara
    -0.61
    istical
    -0.59
    POSITIVE LOGITS
     Commons
    1.39
    ensical
    0.93
    workshop
    0.91
    cape
    0.91
    peak
    0.90
    pread
    0.89
    ĸļ
    0.89
     commons
    0.82
    halla
    0.81
    hire
    0.81
    Activations Density 0.006%

    No Known Activations