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. 2123
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic events and financial matters, particularly involving numbers and statistics

    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
    481
    +0.29
    1.4%
    408
    +0.12
    0.6%
    714
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.29
    0.14
    714
    +0.12
    0.09
    384
    +0.11
    0.09
    Negative Logits
    umat
    -0.78
    ocrat
    -0.76
    fell
    -0.76
    ocument
    -0.74
    obook
    -0.74
    uma
    -0.74
    matter
    -0.74
    olla
    -0.74
    rio
    -0.73
    scribe
    -0.73
    POSITIVE LOGITS
     assorted
    1.08
     willingness
    1.06
     inability
    1.01
     occasional
    0.99
     lack
    0.98
     penchant
    0.97
     consequ
    0.92
     unwillingness
    0.91
     susceptibility
    0.91
     adherence
    0.91
    Activations Density 2.345%

    No Known Activations