© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22567
    Prev
    Next
    INDEX
    Explanations

    the word "often" and its variations, indicating discussions of frequency or recurrence

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    669
    +0.10
    0.4%
    76
    +0.10
    0.4%
    108
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.10
    0.03
    318
    +0.10
    0.03
    278
    +0.09
    0.03
    Negative Logits
    utenberg
    -0.75
    jriwal
    -0.73
    vich
    -0.70
     Achievement
    -0.69
    agate
    -0.69
     Integrity
    -0.68
    rowth
    -0.68
    ngth
    -0.67
    oti
    -0.67
    achev
    -0.67
    POSITIVE LOGITS
    entimes
    1.63
     overlooked
    1.31
     times
    1.18
    times
    1.16
     misunderstood
    1.05
     referred
    1.03
     mistaken
    1.03
     forgotten
    1.01
     cited
    0.95
     mistakenly
    0.94
    Activations Density 0.052%

    No Known Activations