© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21127
    Prev
    Next
    INDEX
    Explanations

    mentions of carbon-related terms, including "carbon tax," "carbon cycle," "carbon sink," and "carbon footprint."

    oai_token-act-pair · gpt-3.5-turbo

    references to carbon and its environmental impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niet
    -0.81
     Psychiatric
    -0.68
     Sloven
    -0.66
     ORDER
    -0.65
    enger
    -0.64
     Order
    -0.64
    rooms
    -0.64
     Mayweather
    -0.62
    alions
    -0.62
     Akin
    -0.61
    POSITIVE LOGITS
     dioxide
    1.68
    aceous
    1.20
    ioxide
    1.02
     fibre
    1.02
    ation
    1.00
     emissions
    0.99
     footprint
    0.99
    ate
    0.97
     fiber
    0.96
    ated
    0.95
    Activations Density 0.030%

    No Known Activations