© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19368
    Prev
    Next
    INDEX
    Explanations

    information about giveaways, contests, promotions, and subscription services

    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
    314
    +0.15
    0.7%
    308
    +0.12
    0.6%
    756
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.15
    -0.03
    546
    +0.12
    0.03
    599
    +0.10
    0.03
    Negative Logits
     clutch
    -0.60
     incent
    -0.59
     accompl
    -0.58
    ocious
    -0.58
    emo
    -0.58
     ego
    -0.58
    pless
    -0.57
     maximizing
    -0.56
     maximize
    -0.53
     humility
    -0.52
    POSITIVE LOGITS
     Territories
    0.82
     Province
    0.77
    isine
    0.74
    Ô
    0.74
     territories
    0.71
    é¾į
    0.71
    URR
    0.70
    éĥ
    0.69
     imports
    0.69
     imported
    0.67
    Activations Density 0.818%

    No Known Activations