© 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. 12416
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development, such as refactoring and codebase improvements

    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
    640
    +0.27
    1.3%
    447
    +0.23
    1.1%
    373
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.27
    0.08
    160
    +0.23
    0.08
    442
    +0.15
    0.06
    Negative Logits
     claws
    -0.74
     wet
    -0.72
     hands
    -0.72
     sustained
    -0.68
     neighb
    -0.68
     escal
    -0.67
     claw
    -0.66
     unre
    -0.66
     melted
    -0.65
     choked
    -0.65
    POSITIVE LOGITS
    ccording
    1.53
    When
    1.45
    Whether
    1.45
    Although
    1.43
    Since
    1.42
    Sometimes
    1.41
    There
    1.41
    While
    1.41
    Before
    1.39
    Because
    1.37
    Activations Density 0.147%

    No Known Activations