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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9028
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic and political commentary, government actions, and societal issues

    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
    480
    +0.27
    1.3%
    481
    +0.13
    0.6%
    73
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.27
    0.10
    762
    +0.13
    0.10
    288
    +0.10
    0.11
    Negative Logits
    dimension
    -0.59
    ãĥĪ
    -0.58
    ãĥĻ
    -0.57
    \":
    -0.55
    å°Ĩ
    -0.55
    ewitness
    -0.54
    ãĥŀ
    -0.52
    ãģĹ
    -0.51
    itely
    -0.50
    pires
    -0.49
    POSITIVE LOGITS
    ;
    1.12
     whereas
    1.01
     because
    1.01
    .;
    0.99
     though
    0.98
     although
    0.95
     but
    0.93
     however
    0.88
     unless
    0.83
    .
    0.82
    Activations Density 1.433%

    No Known Activations