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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 843
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental issues and regulations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.13
    0.6%
    644
    +0.11
    0.5%
    284
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    561
    +0.13
    0.02
    284
    +0.11
    0.02
    575
    +0.11
    0.02
    Negative Logits
    doms
    -0.88
    xus
    -0.79
    dom
    -0.77
    aptic
    -0.76
    loading
    -0.76
    lua
    -0.75
    jong
    -0.73
     McGee
    -0.73
    TOP
    -0.72
    lique
    -0.71
    POSITIVE LOGITS
     hazards
    1.08
    ist
    1.04
     degradation
    0.97
    ists
    0.97
     footprint
    0.96
     stewards
    0.94
     hazard
    0.90
     pollution
    0.90
     sustainability
    0.89
     protections
    0.89
    Activations Density 0.030%

    No Known Activations