© 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. 4013
    Prev
    Next
    INDEX
    Explanations

    information related to the founding of organizations or institutions

    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
    447
    +0.11
    0.5%
    634
    +0.10
    0.5%
    612
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    612
    +0.11
    0.03
    25
    +0.10
    0.02
    725
    +0.10
    0.02
    Negative Logits
    âĨij
    -0.73
     degradation
    -0.64
     wash
    -0.63
    ãĥĺãĥ©
    -0.62
    bole
    -0.61
     shove
    -0.60
     override
    -0.59
    appro
    -0.59
     blot
    -0.59
     inconvenience
    -0.58
    POSITIVE LOGITS
    ablished
    0.89
    quartered
    0.84
     anew
    0.83
     headquartered
    0.74
    reprene
    0.73
    urat
    0.72
    prising
    0.69
     founded
    0.67
     1946
    0.67
     Kad
    0.65
    Activations Density 0.072%

    No Known Activations