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. 11834
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental regulations and government acts

    oai_token-act-pair · gpt-3.5-turbo

    references to environmental legislation and initiatives

    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
     pse
    -0.85
     brass
    -0.81
    agents
    -0.76
    yond
    -0.76
     astronomers
    -0.75
    onyms
    -0.75
     mates
    -0.72
     castles
    -0.71
    uers
    -0.71
     flesh
    -0.71
    POSITIVE LOGITS
     Initiative
    1.71
     Act
    1.63
     Partnership
    1.51
     Program
    1.42
     Reduction
    1.40
     Improvement
    1.38
     Amendments
    1.38
     Enhancement
    1.38
     Assistance
    1.37
     Fund
    1.36
    Activations Density 0.270%

    No Known Activations