© 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. 21180
    Prev
    Next
    INDEX
    Explanations

    words related to technology, software, and entertainment references

    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
    230
    +0.12
    0.6%
    190
    +0.09
    0.4%
    218
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.12
    0.07
    616
    +0.09
    0.06
    230
    +0.09
    0.05
    Negative Logits
     Challenges
    -0.72
     Solitaire
    -0.69
     Taxes
    -0.68
     Tags
    -0.67
     charms
    -0.66
     correctness
    -0.65
     syndrome
    -0.65
     Libraries
    -0.64
     positives
    -0.64
     Grants
    -0.64
    POSITIVE LOGITS
    acious
    1.08
    famous
    1.02
    uous
    1.01
    named
    1.01
    oried
    0.94
    entious
    0.94
    arious
    0.94
    orious
    0.93
    uously
    0.91
    listed
    0.91
    Activations Density 0.435%

    No Known Activations