Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 1520
    Prev
    Next
    INDEX
    Explanations

    phrases related to climate change

    oai_token-act-pair · gpt-3.5-turbo

    references to climate change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.83
    alties
    -0.76
    ittal
    -0.73
    \-
    -0.73
    minster
    -0.71
    amina
    -0.71
    lime
    -0.71
    ealing
    -0.70
    dom
    -0.69
    aban
    -0.69
    POSITIVE LOGITS
     climate
    1.42
    climate
    1.25
     Climate
    1.14
     climates
    1.14
     warming
    1.01
    Climate
    0.99
     clim
    0.87
     fluctuations
    0.80
     warmer
    0.79
     ecology
    0.79
    Activations Density 0.015%

    No Known Activations