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. 2153
    Prev
    Next
    INDEX
    Explanations

    words related to weather and natural disasters

    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
    666
    +0.11
    0.5%
    271
    +0.09
    0.4%
    537
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.11
    0.06
    570
    +0.09
    0.01
    714
    +0.09
    0.05
    Negative Logits
    IQ
    -0.95
     Ethics
    -0.83
    FN
    -0.83
     vanity
    -0.83
     ethical
    -0.82
    Privacy
    -0.81
    =-=-=-=-
    -0.80
     Token
    -0.79
     ethics
    -0.79
     altru
    -0.78
    POSITIVE LOGITS
     rains
    1.57
     rainfall
    1.57
     temperatures
    1.53
     precipitation
    1.52
     weather
    1.31
     humidity
    1.31
     storms
    1.26
     rain
    1.25
     landfall
    1.23
     showers
    1.23
    Activations Density 2.821%

    No Known Activations