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. 10-RES-JB
    6. 9504
    Prev
    Next
    INDEX
    Explanations

    company names and entities related to the energy sector

    oai_token-act-pair · gpt-3.5-turbo

    names of companies and industries related to energy, brewing, entertainment, and construction

    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
    inventoryQuantity
    -0.91
     mindless
    -0.68
    wikipedia
    -0.67
     anger
    -0.67
     hamstring
    -0.67
     invis
    -0.67
     arbitrary
    -0.67
     swimming
    -0.67
     scaven
    -0.66
     statistic
    -0.66
    POSITIVE LOGITS
     Ltd
    1.76
     LLC
    1.64
     Solutions
    1.63
     Corp
    1.57
     Company
    1.55
     Inc
    1.54
     Corporation
    1.45
     Partners
    1.37
     Holdings
    1.36
     Products
    1.36
    Activations Density 0.195%

    No Known Activations