© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 12591
    Prev
    Next
    INDEX
    Explanations

    words related to environmental topics

    oai_token-act-pair · gpt-3.5-turbo

    references to environmental topics and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.73
     nob
    -0.72
     stub
    -0.71
    gin
    -0.70
    stretched
    -0.67
     stret
    -0.66
     revenge
    -0.65
     latt
    -0.64
     tricks
    -0.64
     rul
    -0.63
    POSITIVE LOGITS
     Environmental
    3.59
    Environmental
    2.71
     environmental
    2.11
     Environment
    2.02
     EPA
    1.79
     Climate
    1.64
     environmentalists
    1.63
    Environment
    1.62
    environment
    1.55
    EPA
    1.55
    Activations Density 0.011%

    No Known Activations