© 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. 7-RES-JB
    11. 11753
    Prev
    Next
    INDEX
    Explanations

    mentions of climate change

    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 @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittal
    -0.87
    ioned
    -0.82
    avering
    -0.81
    wered
    -0.80
    ittle
    -0.74
    aird
    -0.73
    ments
    -0.73
     Niet
    -0.73
    ery
    -0.73
    alties
    -0.72
    POSITIVE LOGITS
     climate
    1.07
     climates
    1.04
     Change
    0.99
     warming
    0.96
     change
    0.96
     impacts
    0.93
     Climate
    0.92
     catastrophe
    0.90
     instability
    0.88
     extremes
    0.88
    Activations Density 0.025%

    No Known Activations