Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 18331
    Prev
    Next
    INDEX
    Explanations

    mentions of percentage reduction targets for carbon emissions

    oai_token-act-pair · gpt-3.5-turbo

    references to goals related to emission reduction and climate action targets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spiel
    -0.86
     experien
    -0.83
     Psychiat
    -0.79
    aternity
    -0.77
     Chess
    -0.75
     Poker
    -0.75
    DragonMagazine
    -0.73
     Cantor
    -0.73
     chess
    -0.71
     Oss
    -0.70
    POSITIVE LOGITS
     emissions
    1.77
     greenhouse
    1.70
     pollution
    1.58
     pollutants
    1.48
     carbon
    1.46
     pollut
    1.43
     emission
    1.37
     emit
    1.37
     emitting
    1.37
     deforestation
    1.36
    Activations Density 0.444%

    No Known Activations