© 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. 13771
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to electronic technology, such as "Electromagnetic" and "PCB plating"

    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
    314
    +0.17
    0.8%
    288
    +0.14
    0.7%
    149
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.17
    0.02
    456
    +0.14
    0.02
    314
    +0.11
    0.01
    Negative Logits
    acca
    -0.67
     Grounds
    -0.62
     bott
    -0.61
    iday
    -0.61
    hao
    -0.59
    Lens
    -0.59
     Airways
    -0.58
     Redemption
    -0.58
     Burk
    -0.57
     NETWORK
    -0.56
    POSITIVE LOGITS
    ron
    1.36
    rics
    1.33
    rification
    1.30
    ronic
    1.27
    rical
    1.26
    ronics
    1.24
    roc
    1.24
    rified
    1.21
    rons
    1.20
    RON
    1.16
    Activations Density 0.023%

    No Known Activations