© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8075
    Prev
    Next
    INDEX
    Explanations

    descriptions of characters in a story, focusing on negative traits and relationships

    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
    756
    +0.21
    1.0%
    481
    +0.20
    0.9%
    539
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.21
    0.06
    756
    +0.20
    -0.01
    645
    +0.10
    0.04
    Negative Logits
    ãĤ¡
    -0.69
    Ru
    -0.69
    ãĤ´
    -0.64
    ãĥĨãĤ£
    -0.62
    ãĤ´ãĥ³
    -0.61
    ittance
    -0.59
    @#&
    -0.57
    £ı
    -0.57
    imbabwe
    -0.57
    ichi
    -0.57
    POSITIVE LOGITS
     CLR
    0.59
     Folder
    0.57
     Both
    0.57
     Difference
    0.56
     CST
    0.56
    ucer
    0.55
     PHI
    0.53
     Shades
    0.53
    orem
    0.53
    agree
    0.52
    Activations Density 0.480%

    No Known Activations