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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 18477
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental protection agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to environmental protection and related agencies or concepts

    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
    ucha
    -0.63
    ettle
    -0.60
    Äĩ
    -0.59
     resided
    -0.59
     Jinn
    -0.58
    akia
    -0.58
     diabetic
    -0.57
     spontaneously
    -0.56
     Rowling
    -0.55
     capt
    -0.55
    POSITIVE LOGITS
     Agency
    0.86
     Conservation
    0.85
    conservancy
    0.81
     Environment
    0.74
     Bureau
    0.70
     Directorate
    0.68
     Enhancement
    0.68
     Protection
    0.67
     Policies
    0.67
    gency
    0.66
    Activations Density 0.075%

    No Known Activations