© 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. 4544
    Prev
    Next
    INDEX
    Explanations

    phrases related to expansion and inclusion

    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
    608
    +0.16
    0.7%
    104
    +0.13
    0.6%
    451
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.16
    0.05
    104
    +0.13
    0.03
    508
    +0.11
    0.03
    Negative Logits
     Mehran
    -0.65
     congr
    -0.65
    ato
    -0.65
    tar
    -0.65
    click
    -0.62
    achy
    -0.62
    luck
    -0.61
     Rebell
    -0.60
    achev
    -0.60
     floated
    -0.59
    POSITIVE LOGITS
     encompass
    1.47
     include
    1.04
     accommodate
    0.95
     broaden
    0.92
     extend
    0.84
     exclude
    0.82
     Include
    0.81
    ãĤ¨ãĥ«
    0.79
     penetrate
    0.76
     incorporate
    0.76
    Activations Density 0.115%

    No Known Activations