© 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. 5999
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    +0.43
    2.2%
    447
    +0.24
    1.2%
    266
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    632
    +0.43
    0.07
    43
    +0.24
    0.05
    380
    +0.14
    0.05
    Negative Logits
    minster
    -0.61
    ļéĨĴ
    -0.58
    venth
    -0.57
    ãĥ³ãĤ¸
    -0.56
    ogether
    -0.55
    assed
    -0.55
    staking
    -0.54
     exting
    -0.53
    Ý
    -0.53
    ãĤ´ãĥ³
    -0.52
    POSITIVE LOGITS
     however
    0.69
     please
    0.67
     we
    0.62
     Canaver
    0.59
     astronomers
    0.55
     there
    0.53
    please
    0.53
     Kejriwal
    0.53
     Bengals
    0.52
     Naruto
    0.52
    Activations Density 0.322%

    No Known Activations