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. 1568
    Prev
    Next
    INDEX
    Explanations

    information about legal statements and actions

    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
    679
    +0.13
    0.6%
    447
    +0.09
    0.4%
    512
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.13
    0.09
    468
    +0.09
    0.09
    417
    +0.09
    0.09
    Negative Logits
    Pont
    -0.84
    à¦
    -0.79
    pee
    -0.73
    ãĥĬ
    -0.68
    ãĥ¯ãĥ³
    -0.68
    kay
    -0.67
    nic
    -0.66
    estern
    -0.65
    irrel
    -0.65
    gone
    -0.65
    POSITIVE LOGITS
     goodbye
    0.94
     afterward
    0.81
     they
    0.80
     yesterday
    0.79
     bluntly
    0.78
     afterwards
    0.76
     he
    0.76
    :"
    0.72
     Monday
    0.71
     sarcast
    0.71
    Activations Density 0.634%

    No Known Activations