© 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. 12413
    Prev
    Next
    INDEX
    Explanations

    terms related to the field of lab work, such as lab results, lab technicians, and lab experiments

    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
    26
    +0.09
    0.4%
    211
    +0.09
    0.4%
    140
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.09
    0.01
    46
    +0.09
    0.01
    26
    +0.09
    0.01
    Negative Logits
     Marketable
    -0.68
    lihood
    -0.65
    theless
    -0.64
     Ceres
    -0.62
     Resolution
    -0.61
     antiquity
    -0.60
     chant
    -0.60
     indiscrim
    -0.59
     understatement
    -0.59
     DARK
    -0.59
    POSITIVE LOGITS
    yrinth
    1.68
    rador
    1.52
    elled
    1.35
    orers
    1.32
    elling
    1.32
    orer
    1.25
    eled
    1.19
    els
    1.19
    rosse
    1.18
    eling
    1.11
    Activations Density 0.016%

    No Known Activations