© 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. 5474
    Prev
    Next
    INDEX
    Explanations

    dates or time markers that are used to structure a report or event timeline

    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
    267
    +0.12
    0.6%
    237
    +0.09
    0.4%
    662
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.12
    0.03
    168
    +0.09
    0.03
    237
    +0.08
    0.03
    Negative Logits
    ties
    -0.69
    ded
    -0.61
    ische
    -0.60
     otherwise
    -0.59
    orum
    -0.59
    idad
    -0.58
    cv
    -0.58
    ses
    -0.58
    making
    -0.56
    maker
    -0.55
    POSITIVE LOGITS
    adays
    0.87
     secondly
    0.81
     Comes
    0.76
    ebus
    0.75
     proceeded
    0.75
    Ļ½
    0.74
     comes
    0.73
     came
    0.73
    noon
    0.72
    ulhu
    0.67
    Activations Density 0.038%

    No Known Activations