© 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. 7983
    Prev
    Next
    INDEX
    Explanations

    phrases related to future plans or outcomes

    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
    171
    +0.13
    0.6%
    763
    +0.12
    0.5%
    434
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.13
    0.04
    183
    +0.12
    0.03
    763
    +0.09
    0.03
    Negative Logits
     Coach
    -0.68
     Mages
    -0.62
     thous
    -0.61
     Arena
    -0.60
     coach
    -0.59
     Rampage
    -0.57
    Ü
    -0.56
    ascript
    -0.54
     Bounty
    -0.53
     Dota
    -0.53
    POSITIVE LOGITS
    pload
    0.84
    iw
    0.78
    roads
    0.74
    ggles
    0.71
    conom
    0.69
    hearted
    0.69
    eyed
    0.69
    hots
    0.67
    rive
    0.67
    wolves
    0.67
    Activations Density 0.304%

    No Known Activations