© 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. 7437
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and reactions from different groups

    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
    314
    +0.13
    0.6%
    566
    +0.11
    0.5%
    319
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.13
    0.03
    552
    +0.11
    0.03
    605
    +0.10
    0.03
    Negative Logits
    Soc
    -0.66
    âĺħ
    -0.64
    ethy
    -0.64
     presently
    -0.62
     currently
    -0.62
    ãĥĺãĥ©
    -0.58
    *****
    -0.57
     Currently
    -0.55
    urden
    -0.55
    next
    -0.55
    POSITIVE LOGITS
     dealings
    0.97
     trouble
    0.85
    drawn
    0.81
     difficulty
    0.79
     undergone
    0.79
    oken
    0.77
     recourse
    0.77
     plenty
    0.76
     success
    0.76
    iths
    0.73
    Activations Density 0.052%

    No Known Activations