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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 182
    Prev
    Next
    INDEX
    Explanations

    positive evaluations or opinions about sports players and teams

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    663
    +0.13
    0.6%
    107
    +0.12
    0.5%
    196
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.13
    0.14
    663
    +0.12
    0.11
    107
    +0.10
    0.10
    Negative Logits
     Hebdo
    -0.70
     Gap
    -0.62
     guiActiveUnfocused
    -0.61
    VERTISEMENT
    -0.59
     ///
    -0.58
     interoper
    -0.58
    Creat
    -0.57
    artney
    -0.56
     vanished
    -0.56
     dwind
    -0.56
    POSITIVE LOGITS
     myself
    1.36
     personally
    1.11
     glad
    0.94
    poke
    0.90
     regret
    0.89
     recommend
    0.87
    oan
    0.85
    heart
    0.84
     think
    0.84
     believe
    0.84
    Activations Density 2.281%

    No Known Activations