© 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. 20860
    Prev
    Next
    INDEX
    Explanations

    references to climate change and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of climate change

    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
    -0.82
    ioned
    -0.82
    ments
    -0.77
    umbn
    -0.75
     Caldwell
    -0.70
    dos
    -0.68
    phabet
    -0.67
    ittle
    -0.66
    imity
    -0.66
    ery
    -0.66
    POSITIVE LOGITS
     change
    1.35
     Change
    1.17
    change
    1.10
    Change
    1.02
     catastrophe
    0.99
     warming
    0.96
     sensitivity
    0.93
     extremes
    0.93
     science
    0.91
     scept
    0.89
    Activations Density 0.030%

    No Known Activations