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. 0-RES-JB
    6. 4405
    Prev
    Next
    INDEX
    Explanations

    references to different types of firms or companies

    oai_token-act-pair · gpt-3.5-turbo

    references to companies or businesses

    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
     Commander
    -0.71
    aton
    -0.69
     Survivor
    -0.66
     Divinity
    -0.62
     commander
    -0.61
     Authorization
    -0.59
    love
    -0.59
     Creator
    -0.59
     Companion
    -0.59
    olation
    -0.59
    POSITIVE LOGITS
     firms
    3.57
     companies
    2.27
     firm
    2.22
    Companies
    1.99
     businesses
    1.73
     Companies
    1.72
     enterprises
    1.71
     corporations
    1.65
     industries
    1.59
    irms
    1.53
    Activations Density 0.013%

    No Known Activations