© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 17
    Prev
    Next
    INDEX
    Explanations

    studies and discussions related to the impact of minimum wage increases on employment

    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
    718
    +0.10
    0.5%
    74
    +0.10
    0.4%
    388
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.10
    0.11
    690
    +0.10
    0.07
    49
    +0.09
    0.09
    Negative Logits
     Ded
    -0.71
     Petty
    -0.70
     Kut
    -0.69
     Tot
    -0.67
     Lists
    -0.67
    cknowled
    -0.67
     typed
    -0.66
     Elements
    -0.66
     ital
    -0.66
    Pie
    -0.65
    POSITIVE LOGITS
     beneficial
    1.23
     synerg
    1.16
     impair
    1.14
     harm
    1.14
    acea
    1.10
     adversely
    1.07
     enhance
    1.05
     affect
    1.05
     inhibit
    1.05
     alleviate
    1.03
    Activations Density 2.071%

    No Known Activations