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. 0-RES-JB
    6. 5733
    Prev
    Next
    INDEX
    Explanations

    words related to environmental conservation organizations or activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental conservation

    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
     sensitive
    -0.68
     unre
    -0.67
    ¯
    -0.66
     swear
    -0.66
     batter
    -0.65
     diss
    -0.65
     bet
    -0.65
     accuser
    -0.65
     unreal
    -0.64
     lip
    -0.64
    POSITIVE LOGITS
     Conservation
    3.67
     Fisheries
    1.44
     Forestry
    1.38
     Correctional
    1.38
     Preservation
    1.38
     Ecology
    1.37
     Conserv
    1.32
     Wildlife
    1.32
     Corrections
    1.23
     Wilderness
    1.21
    Activations Density 0.024%

    No Known Activations