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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11354
    Prev
    Next
    INDEX
    Explanations

    information related to tropical storms and their impacts

    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
    +0.15
    0.7%
    623
    +0.13
    0.6%
    362
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.02
    623
    +0.13
    0.01
    599
    +0.10
    0.01
    Negative Logits
    brance
    -0.87
     Mellon
    -0.85
    umbn
    -0.83
    usable
    -0.83
    viation
    -0.81
    avering
    -0.80
    edin
    -0.79
    Merit
    -0.78
    adr
    -0.76
    baugh
    -0.76
    POSITIVE LOGITS
     tropical
    0.94
     fruits
    0.94
     climates
    0.92
     forests
    0.92
     islands
    0.90
     jungle
    0.89
     paradise
    0.86
     humid
    0.85
     forest
    0.85
     deforestation
    0.85
    Activations Density 0.030%

    No Known Activations