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 3072
    5. 8-RES_FS3072-JB
    6. 835
    Prev
    Next
    INDEX
    Explanations

    discussions related to sports contracts and player decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    602
    +0.10
    0.5%
    74
    +0.09
    0.4%
    188
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.19
    618
    +0.09
    0.13
    602
    +0.09
    0.07
    Negative Logits
     Feminist
    -0.85
     NGOs
    -0.83
     mobil
    -0.82
     UNESCO
    -0.81
     NGO
    -0.80
     barr
    -0.80
     authorised
    -0.79
     ®
    -0.78
     scept
    -0.78
     para
    -0.76
    POSITIVE LOGITS
     offseason
    1.60
    Coach
    1.51
     rookie
    1.49
     Rookie
    1.49
    NFL
    1.47
     preseason
    1.45
     Playoff
    1.45
     rookies
    1.42
     playoff
    1.41
     Bucs
    1.40
    Activations Density 4.364%

    No Known Activations