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 3072
    5. 8-RES_FS3072-JB
    6. 2835
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration, partnership, and working together towards a common goal

    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
    616
    +0.11
    0.5%
    513
    +0.10
    0.4%
    251
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.11
    0.05
    205
    +0.10
    0.05
    513
    +0.10
    0.05
    Negative Logits
    ysis
    -0.77
    ble
    -0.67
    holes
    -0.66
    geon
    -0.65
    hole
    -0.63
    geons
    -0.62
     livest
    -0.62
    stakes
    -0.61
    letters
    -0.60
    ako
    -0.59
    POSITIVE LOGITS
     bargaining
    0.72
    arity
    0.72
    iliation
    0.71
    ortium
    0.71
    hall
    0.70
     effort
    0.66
    ãĤ¤ãĥĪ
    0.66
     disparate
    0.66
     Chiefs
    0.66
     cohesion
    0.65
    Activations Density 0.737%

    No Known Activations