© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16386
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of emissions, particularly related to pollution or gases

    oai_token-act-pair · gpt-3.5-turbo

    references to greenhouse gas emissions

    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
     Struggle
    -0.76
    mart
    -0.74
     Semin
    -0.74
    arch
    -0.73
    vet
    -0.72
     Lad
    -0.71
    kid
    -0.69
    ghan
    -0.69
    juven
    -0.67
    atched
    -0.67
    POSITIVE LOGITS
     emissions
    3.40
     emission
    2.75
     pollution
    1.82
     greenhouse
    1.75
     emit
    1.73
     emitted
    1.70
     pollutants
    1.61
     emitting
    1.59
     methane
    1.58
     carbon
    1.57
    Activations Density 0.022%

    No Known Activations