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. 11848
    Prev
    Next
    INDEX
    Explanations

    mentions of companies or corporate entities

    oai_token-act-pair · gpt-3.5-turbo

    references to companies and corporations

    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
    718
    -0.72
    rawdownloadcloneembedreportprint
    -0.67
    theless
    -0.66
     RELEASE
    -0.65
    WARE
    -0.65
    isite
    -0.65
    lihood
    -0.64
     LIB
    -0.63
     Nights
    -0.62
     Fulton
    -0.62
    POSITIVE LOGITS
     executives
    1.02
     companies
    0.91
    afety
    0.91
     CEOs
    0.89
     firms
    0.84
    mens
    0.83
     corporations
    0.83
    folk
    0.82
     mogul
    0.82
     nomine
    0.80
    Activations Density 0.038%

    No Known Activations