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 · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 21652
    Prev
    Next
    INDEX
    Explanations

    descriptions of natural environments and extreme weather conditions

    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
    742
    +0.11
    0.5%
    474
    +0.10
    0.4%
    166
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.11
    0.04
    742
    +0.10
    0.03
    573
    +0.10
    0.03
    Negative Logits
    FN
    -0.88
    tein
    -0.87
     successors
    -0.86
    folios
    -0.86
    actionDate
    -0.81
    thood
    -0.81
     successor
    -0.77
    acebook
    -0.75
     Memor
    -0.73
    IQ
    -0.73
    POSITIVE LOGITS
     raining
    1.12
     humidity
    1.06
     showers
    1.04
     haze
    1.02
     rains
    1.01
     precipitation
    0.98
     rain
    0.96
    oxide
    0.94
     intermitt
    0.93
     coating
    0.92
    Activations Density 0.383%

    No Known Activations