© 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. 11092
    Prev
    Next
    INDEX
    Explanations

    political and military terms and contexts

    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
    373
    +0.18
    0.9%
    230
    +0.13
    0.6%
    244
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.18
    0.05
    244
    +0.13
    0.04
    373
    +0.09
    -0.00
    Negative Logits
    ties
    -0.69
    Ļ½
    -0.65
     perspect
    -0.62
    mate
    -0.62
     makeshift
    -0.62
     retri
    -0.60
    graded
    -0.59
    fulness
    -0.59
     wound
    -0.58
     hindsight
    -0.57
    POSITIVE LOGITS
     Continue
    1.01
     Advertisement
    0.98
    advertisement
    0.77
    Skip
    0.72
    usercontent
    0.69
    Advertisement
    0.69
    ieu
    0.68
    Credit
    0.67
    sburg
    0.65
     @@
    0.65
    Activations Density 0.015%

    No Known Activations