© 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. 49
    Prev
    Next
    INDEX
    Explanations

    information related to video game development and community updates

    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
    +0.37
    1.9%
    481
    +0.20
    1.0%
    480
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.37
    0.10
    288
    +0.20
    0.10
    167
    +0.16
    -0.00
    Negative Logits
     ÂŃ
    -0.82
     Hussein
    -0.75
     Rodham
    -0.71
     strikingly
    -0.68
     Ronald
    -0.65
    utterstock
    -0.63
     Beir
    -0.63
     Hasan
    -0.63
     Lyndon
    -0.62
     reportedly
    -0.62
    POSITIVE LOGITS
     devs
    0.92
    hack
    0.89
     pokemon
    0.83
    coin
    0.83
     ;)
    0.82
     :)
    0.81
     mods
    0.80
     :(
    0.79
     lvl
    0.79
     tho
    0.79
    Activations Density 1.165%

    No Known Activations