© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11219
    Prev
    Next
    INDEX
    Explanations

    quantities related to environmental resources like carbon, water, oil, and pollution

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements related to environmental resources and pollution

    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
    actionDate
    -0.66
     priorities
    -0.63
     precedence
    -0.63
    winner
    -0.62
    Kings
    -0.61
    ĻĤ
    -0.60
     priority
    -0.58
    NOR
    -0.58
     Mothers
    -0.57
    Stretch
    -0.57
    POSITIVE LOGITS
     tonnes
    0.96
    poons
    0.91
     annually
    0.88
     worth
    0.88
     of
    0.87
     per
    0.87
     cubic
    0.86
    awatts
    0.83
     lbs
    0.83
     thereof
    0.83
    Activations Density 0.103%

    No Known Activations