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. 21207
    Prev
    Next
    INDEX
    Explanations

    organizations and initiatives related to environmental conservation and public health

    oai_token-act-pair · gpt-3.5-turbo

    references to various global health and wildlife organizations

    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
    paio
    -0.74
    uman
    -0.73
    hent
    -0.73
    outhern
    -0.72
     muzzle
    -0.71
    esville
    -0.67
    ordable
    -0.64
     mids
    -0.61
     intern
    -0.61
    acle
    -0.61
    POSITIVE LOGITS
     Organisation
    1.08
     Organization
    1.00
     Programme
    0.89
     Rankings
    0.87
     Warcraft
    0.85
     Prize
    0.80
     Forum
    0.79
     Workshop
    0.74
     Fund
    0.73
     Picture
    0.72
    Activations Density 0.069%

    No Known Activations