© 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. 14713
    Prev
    Next
    INDEX
    Explanations

    phrases requesting communication or feedback

    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
    517
    +0.10
    0.4%
    748
    +0.09
    0.4%
    726
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.10
    0.02
    748
    +0.09
    0.01
    424
    +0.09
    0.01
    Negative Logits
    adic
    -0.70
     Demons
    -0.65
    olid
    -0.62
    ©¶æ
    -0.62
    tan
    -0.61
    SEA
    -0.60
    Downloadha
    -0.59
    erva
    -0.59
    allowed
    -0.59
    Rap
    -0.58
    POSITIVE LOGITS
     beforehand
    0.90
     ASAP
    0.87
     how
    0.84
    ledge
    0.75
    ledged
    0.75
     exactly
    0.75
     promptly
    0.72
     firsthand
    0.71
     via
    0.71
     tid
    0.70
    Activations Density 0.025%

    No Known Activations