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. 1-RES-JB
    6. 4508
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental destruction, specifically focused on deforestation

    oai_token-act-pair · gpt-3.5-turbo

    references to deforestation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abus
    -0.86
    dat
    -0.82
    atory
    -0.80
    PAR
    -0.80
    enger
    -0.78
    arsity
    -0.74
    Card
    -0.73
    rosse
    -0.73
    Column
    -0.73
    ently
    -0.72
    POSITIVE LOGITS
     forests
    1.06
     deforestation
    1.05
    forest
    0.99
    forestation
    0.98
     plantations
    0.93
     Forest
    0.85
     Forestry
    0.79
     forest
    0.78
    nesday
    0.77
     Trees
    0.75
    Activations Density 0.015%

    No Known Activations