© 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. 17475
    Prev
    Next
    INDEX
    Explanations

    legal terms and language related to the interpretation and application of laws

    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
    679
    +0.17
    0.8%
    640
    +0.11
    0.5%
    145
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.17
    0.12
    679
    +0.11
    0.11
    145
    +0.10
    0.09
    Negative Logits
     favourite
    -0.83
     favourites
    -0.79
     nicer
    -0.78
     worsh
    -0.78
     hooked
    -0.77
     moons
    -0.77
     skinny
    -0.76
     immortal
    -0.76
     unlucky
    -0.76
     fancy
    -0.75
    POSITIVE LOGITS
     Accordingly
    1.76
     Therefore
    1.64
     Consequently
    1.58
     Moreover
    1.56
     Furthermore
    1.52
     Additionally
    1.51
     Notwithstanding
    1.48
     However
    1.47
     Thus
    1.47
     Specifically
    1.42
    Activations Density 0.480%

    No Known Activations