© 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 EvalsExportsinterp-engineNEWAPI 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. 5579
    Prev
    Next
    INDEX
    Explanations

    references to political figures and controversies

    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
    481
    +0.34
    1.7%
    447
    +0.17
    0.8%
    37
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.34
    0.06
    668
    +0.17
    0.04
    430
    +0.10
    0.08
    Negative Logits
     Pione
    -0.69
     generations
    -0.63
     %%
    -0.63
     Soviets
    -0.62
    ween
    -0.62
    ewater
    -0.60
    database
    -0.59
    Basic
    -0.59
     Pattern
    -0.59
     probabilities
    -0.58
    POSITIVE LOGITS
     tweeted
    1.44
     tweeting
    1.27
     retweet
    1.27
     angrily
    1.17
     tweets
    1.11
     apologized
    1.11
     reportedly
    1.04
     rant
    1.04
     disav
    1.04
     tweet
    1.04
    Activations Density 0.666%

    No Known Activations