© 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. 10-RES-JB
    11. 21446
    Prev
    Next
    INDEX
    Explanations

    information related to climate change and global warming

    oai_token-act-pair · gpt-3.5-turbo

    references to climate change and its effects

    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
     Oath
    -0.79
     clerks
    -0.74
     Ghostbusters
    -0.73
     announ
    -0.72
     testers
    -0.68
     Lawyers
    -0.68
     jurors
    -0.68
     Funny
    -0.67
     Bach
    -0.66
     FBI
    -0.65
    POSITIVE LOGITS
     unsustainable
    1.23
     accelerating
    1.03
     interconnected
    1.03
     impover
    1.03
     greenhouse
    1.01
     humankind
    1.00
    arbon
    1.00
     ecological
    0.99
     globalization
    0.98
     global
    0.98
    Activations Density 0.809%

    No Known Activations