© 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. 19684
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions related to programming and computer science

    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
    647
    +0.13
    0.6%
    445
    +0.11
    0.5%
    511
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.13
    0.06
    172
    +0.11
    0.05
    511
    +0.10
    0.05
    Negative Logits
    romy
    -0.75
    udi
    -0.70
    itiveness
    -0.69
    oller
    -0.67
    ivas
    -0.66
    reprene
    -0.66
    iger
    -0.65
    WI
    -0.65
    audi
    -0.64
    edo
    -0.63
    POSITIVE LOGITS
     follows
    1.10
    phy
    1.05
    pires
    1.00
    ynchron
    0.98
    pired
    0.94
    cription
    0.92
    criptions
    0.91
    part
    0.89
    ylum
    0.88
     soon
    0.86
    Activations Density 0.139%

    No Known Activations