© 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. 4858
    Prev
    Next
    INDEX
    Explanations

    important terms or phrases related to various fields such as agriculture, sports, health, and politics

    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
    481
    +0.18
    0.8%
    288
    +0.10
    0.5%
    585
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.09
    325
    +0.10
    0.06
    455
    +0.10
    0.06
    Negative Logits
    selves
    -0.86
     [|
    -0.71
    edIn
    -0.71
     Including
    -0.69
    DERR
    -0.69
    Eva
    -0.69
    Ø©
    -0.68
    ;;;;
    -0.67
     Helpful
    -0.67
    ecause
    -0.64
    POSITIVE LOGITS
    iest
    1.11
     aspect
    0.85
    ultimate
    0.84
    liest
    0.82
     analogy
    0.81
    osphere
    0.79
    osite
    0.75
     portion
    0.75
     gap
    0.74
     question
    0.72
    Activations Density 0.518%

    No Known Activations