© 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. 20890
    Prev
    Next
    INDEX
    Explanations

    phrases related to human trafficking and project management practices

    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
    480
    +0.40
    2.0%
    447
    +0.12
    0.6%
    217
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.40
    -0.00
    351
    +0.12
    0.04
    266
    +0.10
    0.08
    Negative Logits
    bridge
    -0.61
    THER
    -0.60
    viously
    -0.57
    çīĪ
    -0.57
     Had
    -0.56
    Europe
    -0.55
    ?]
    -0.54
    Bridge
    -0.53
     Confederation
    -0.53
    velt
    -0.52
    POSITIVE LOGITS
     usually
    1.06
    usually
    1.02
     invariably
    1.00
     typically
    0.91
    typically
    0.85
    often
    0.81
     inevitably
    0.80
     Usually
    0.79
     predetermined
    0.77
     often
    0.76
    Activations Density 1.067%

    No Known Activations