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. 1624
    Prev
    Next
    INDEX
    Explanations

    pronouns such as "them" and "her," especially when referring to specific actions or objects

    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
    33
    +0.10
    0.4%
    481
    +0.10
    0.4%
    216
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.10
    0.08
    112
    +0.10
    0.06
    354
    +0.09
    0.06
    Negative Logits
    âĢ¢âĢ¢
    -0.66
     Megan
    -0.65
    mire
    -0.62
     Lori
    -0.61
     Fulton
    -0.60
     Salon
    -0.60
    CCC
    -0.60
     LH
    -0.58
     Jon
    -0.58
     Laurie
    -0.57
    POSITIVE LOGITS
    selves
    1.75
    atically
    1.55
     selves
    1.49
    atic
    1.42
    self
    1.42
    alian
    0.94
    atics
    0.94
     conduc
    0.91
     individually
    0.85
    zbollah
    0.83
    Activations Density 0.526%

    No Known Activations