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. 19126
    Prev
    Next
    INDEX
    Explanations

    information related to music albums and productions

    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
    314
    +0.17
    0.8%
    640
    +0.14
    0.7%
    160
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.17
    0.04
    102
    +0.14
    0.04
    442
    +0.13
    0.04
    Negative Logits
     care
    -0.87
     grasp
    -0.86
     matter
    -0.82
     batter
    -0.80
     enrol
    -0.80
     scrambling
    -0.79
     disproportionately
    -0.79
     cler
    -0.79
     quota
    -0.78
     outfielder
    -0.78
    POSITIVE LOGITS
    Eat
    1.34
    Morning
    1.32
    Operation
    1.31
    Dear
    1.27
    Untitled
    1.26
    Big
    1.25
    Night
    1.24
    Golden
    1.23
    Ultimate
    1.23
    Saturday
    1.22
    Activations Density 0.070%

    No Known Activations