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. 11677
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to materials science and engineering

    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
    481
    +0.20
    0.9%
    447
    +0.14
    0.7%
    408
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.05
    575
    +0.14
    0.04
    589
    +0.10
    0.03
    Negative Logits
     Daylight
    -0.68
    BUR
    -0.68
    Lago
    -0.68
    Roy
    -0.66
    wick
    -0.63
     LIST
    -0.63
     encount
    -0.62
    Repe
    -0.61
     Skydragon
    -0.60
    ĺ
    -0.60
    POSITIVE LOGITS
     technologies
    0.96
     projects
    0.89
     project
    0.83
    ists
    0.82
     technology
    0.81
    heid
    0.81
     implants
    0.80
     designs
    0.80
    icity
    0.79
     models
    0.78
    Activations Density 0.152%

    No Known Activations