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. 21346
    Prev
    Next
    INDEX
    Explanations

    nonprofit organizations or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to nonprofit organizations

    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
    -0.77
    stroke
    -0.76
    amura
    -0.75
    uncture
    -0.75
    othy
    -0.75
    pread
    -0.74
    Phones
    -0.74
    arella
    -0.73
    perature
    -0.73
    ravings
    -0.72
    POSITIVE LOGITS
     organization
    1.06
     corporation
    1.04
     entity
    1.02
     fundraising
    0.98
     organizations
    0.97
     organisation
    0.95
     nonprofit
    0.91
    profit
    0.88
     charitable
    0.88
     fundraiser
    0.85
    Activations Density 0.039%

    No Known Activations