© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7894
    Prev
    Next
    INDEX
    Explanations

    quotes and statements made by individuals

    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
    447
    +0.70
    4.9%
    464
    +0.13
    0.9%
    642
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.70
    0.06
    481
    +0.13
    0.14
    585
    +0.10
    0.08
    Negative Logits
    Specifically
    -0.53
    =]
    -0.52
     thereof
    -0.52
     therein
    -0.52
     accordingly
    -0.49
     respectively
    -0.45
     [âĢ¦]
    -0.44
     thereto
    -0.44
    *.
    -0.43
    ."[
    -0.42
    POSITIVE LOGITS
     Zoro
    0.48
     Gard
    0.47
    byss
    0.43
     Scientology
    0.43
     NRL
    0.42
     Canaver
    0.41
     Bihar
    0.41
     Winc
    0.41
     Glou
    0.40
     Correctional
    0.40
    Activations Density 3.273%

    No Known Activations