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. 8-RES-JB
    6. 8720
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of companies and firms, such as marketing companies, consulting firms, and insurance companies

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of companies and firms in a business context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.71
     positives
    -0.67
    hyde
    -0.65
     Abilities
    -0.65
    liest
    -0.58
     belts
    -0.57
     Bagg
    -0.57
    Phones
    -0.57
    ods
    -0.56
    latest
    -0.56
    POSITIVE LOGITS
     specializing
    1.19
     called
    0.95
     affiliated
    0.87
     headquartered
    0.85
     whose
    0.82
     financed
    0.80
     named
    0.79
    ossier
    0.79
     owned
    0.79
     funded
    0.78
    Activations Density 0.306%

    No Known Activations