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. 4-RES-JB
    6. 21462
    Prev
    Next
    INDEX
    Explanations

    terms related to the greenhouse gas carbon dioxide and its effects on the environment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of carbon dioxide

    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
    aws
    -0.79
    HCR
    -0.75
    iage
    -0.70
    ockets
    -0.70
    nee
    -0.69
    things
    -0.69
    pocket
    -0.67
    NT
    -0.67
    ULE
    -0.66
    Kn
    -0.66
    POSITIVE LOGITS
     dioxide
    1.22
     emissions
    1.12
    ioxide
    1.09
     emission
    1.05
     gases
    0.98
     oxide
    0.95
     fumes
    0.91
     gas
    0.91
     emitting
    0.89
     trap
    0.85
    Activations Density 0.022%

    No Known Activations