© 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. 11082
    Prev
    Next
    INDEX
    Explanations

    terms related to legislation or legal matters

    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
    362
    +0.12
    0.6%
    195
    +0.12
    0.6%
    568
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.12
    0.02
    600
    +0.12
    0.02
    408
    +0.12
    0.02
    Negative Logits
    ruary
    -0.95
    ellen
    -0.93
    matched
    -0.83
    ardless
    -0.82
    assis
    -0.79
    arest
    -0.79
    AUT
    -0.78
    nai
    -0.78
    irlf
    -0.78
    ardo
    -0.78
    POSITIVE LOGITS
     activities
    1.15
     activity
    1.10
     pursuits
    1.07
     endeavors
    1.01
     incidents
    1.01
     disasters
    0.98
     phenomena
    0.98
     topics
    0.97
     behaviors
    0.96
     developments
    0.95
    Activations Density 0.038%

    No Known Activations