© 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. 4-RES-JB
    11. 16980
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental topics

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "environment."

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

    No Comments

    Negative Logits
    ilts
    -0.87
    heading
    -0.83
    uster
    -0.82
    mad
    -0.81
    doms
    -0.77
    headed
    -0.72
    aptic
    -0.72
    dom
    -0.72
    arters
    -0.71
    iple
    -0.71
    POSITIVE LOGITS
     Environment
    1.03
     enrichment
    0.81
     conservation
    0.79
    conservancy
    0.77
     Enhancement
    0.75
    Environment
    0.74
     environment
    0.73
     sustainability
    0.73
    Variable
    0.73
     ecology
    0.71
    Activations Density 0.015%

    No Known Activations