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. 10-RES-JB
    6. 12995
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental factors and climate change, specifically focusing on sea level rise

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sea level rise and environmental changes

    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
    cash
    -0.89
    strings
    -0.78
    mega
    -0.72
    Gaming
    -0.70
    Birth
    -0.68
    RET
    -0.67
    folk
    -0.64
    actionDate
    -0.64
    ILY
    -0.64
    string
    -0.63
    POSITIVE LOGITS
     simulator
    0.80
     respir
    0.73
     continuum
    0.69
     preservation
    0.68
     evacuation
    0.67
    giene
    0.66
     vantage
    0.65
     resusc
    0.65
     intrusion
    0.64
    imeters
    0.63
    Activations Density 0.344%

    No Known Activations