© 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. 10-RES-JB
    11. 5529
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to carbon dioxide levels and concentrations in the atmosphere

    oai_token-act-pair · gpt-3.5-turbo

    terms related to carbon dioxide levels and concentrations in the atmosphere

    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
     Tanz
    -0.80
    ĪĴ
    -0.77
    odore
    -0.73
     dexter
    -0.72
     Dominican
    -0.70
    slice
    -0.68
     Malays
    -0.68
     Ital
    -0.66
     Shiv
    -0.66
     Valiant
    -0.66
    POSITIVE LOGITS
     emissions
    1.68
     emission
    1.49
     concentrations
    1.38
     dioxide
    1.38
    ioxide
    1.38
     pollution
    1.36
     emitted
    1.30
     gases
    1.17
     concentration
    1.15
     pollut
    1.12
    Activations Density 0.078%

    No Known Activations