Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 24220
    Prev
    Next
    INDEX
    Explanations

    relevant terms related to business operations and management

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to business practices and sustainability issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.91
     declass
    -0.83
    mire
    -0.82
    raph
    -0.80
     Hannibal
    -0.80
     juven
    -0.69
    RAM
    -0.68
    izoph
    -0.68
     Trey
    -0.68
     Neon
    -0.67
    POSITIVE LOGITS
     businesses
    1.99
    Business
    1.77
     business
    1.74
    business
    1.64
     entrepreneurs
    1.61
     Business
    1.58
     enterprises
    1.53
     businessmen
    1.53
     entrepreneurship
    1.52
     entrepreneurial
    1.49
    Activations Density 0.535%

    No Known Activations