© 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 EvalsExportsinterp-engineNEWAPI 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. 20771
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and products, particularly focusing on specifications and features

    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
    225
    +0.11
    0.5%
    724
    +0.11
    0.5%
    593
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.11
    0.06
    724
    +0.11
    0.06
    255
    +0.10
    0.04
    Negative Logits
    ãĤ±
    -0.84
    ãĤ³
    -0.78
    Pic
    -0.75
    IRC
    -0.73
    Gender
    -0.68
    æĿ
    -0.67
    prep
    -0.65
    Ward
    -0.64
    ignant
    -0.64
    ç«
    -0.61
    POSITIVE LOGITS
     exceeds
    0.90
     ratio
    0.89
     achievable
    0.82
     (<
    0.79
     compared
    0.78
     (>
    0.77
     achieved
    0.77
     (~
    0.77
     equals
    0.76
     estimation
    0.74
    Activations Density 0.173%

    No Known Activations