© 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. 15126
    Prev
    Next
    INDEX
    Explanations

    words related to environmental issues and land ownership

    oai_token-act-pair · gpt-3.5-turbo

    references to environmental effects and sustainability issues related to land and vegetation

    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
     autom
    -0.75
     Robots
    -0.74
    iuses
    -0.73
     waiter
    -0.72
     audi
    -0.71
     impuls
    -0.70
    sych
    -0.70
     Deadpool
    -0.69
     psychiatrists
    -0.69
     secretaries
    -0.69
    POSITIVE LOGITS
     wetlands
    1.34
     farmland
    1.28
     adjacent
    1.27
     southwest
    1.26
     northwest
    1.21
     inland
    1.19
     habitat
    1.18
     adjoining
    1.18
     acre
    1.17
     northeast
    1.16
    Activations Density 1.435%

    No Known Activations