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. 1125
    Prev
    Next
    INDEX
    Explanations

    words related to animals and pets

    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
    167
    +0.12
    0.6%
    48
    +0.10
    0.5%
    191
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.07
    343
    +0.10
    0.05
    48
    +0.10
    0.05
    Negative Logits
    éĹĺ
    -0.78
    DERR
    -0.76
    unda
    -0.73
    artz
    -0.73
    IDER
    -0.72
     sclerosis
    -0.70
     WARN
    -0.70
    ONES
    -0.69
     seeded
    -0.68
     Shap
    -0.68
    POSITIVE LOGITS
    ertodd
    1.00
     puppies
    0.99
    fights
    0.94
     dogs
    0.94
     barking
    0.92
    fight
    0.90
    heter
    0.89
    fighting
    0.87
    riages
    0.87
     pee
    0.85
    Activations Density 0.855%

    No Known Activations