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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 7344
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws, policies, and government actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    393
    +0.10
    0.5%
    248
    +0.10
    0.5%
    384
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.05
    384
    +0.10
    0.04
    328
    +0.09
    0.04
    Negative Logits
    £ı
    -0.91
    anooga
    -0.83
    ĸļ
    -0.81
    rontal
    -0.81
    ulhu
    -0.77
    ouston
    -0.75
    onomous
    -0.75
     Detective
    -0.72
    ĪĴ
    -0.69
    ciating
    -0.69
    POSITIVE LOGITS
     taxes
    1.19
     royalties
    1.14
     cents
    1.07
     expenses
    1.06
     fees
    1.01
     entitle
    0.98
     Taxes
    0.98
     concessions
    0.96
     GST
    0.95
     costs
    0.94
    Activations Density 0.259%

    No Known Activations