© 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 49152
    9. 8-RES_FS49152-JB
    11. 26719
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of mastering skills or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    748
    +0.12
    0.5%
    101
    +0.11
    0.5%
    271
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.01
    748
    +0.11
    0.01
    641
    +0.11
    0.01
    Negative Logits
    uary
    -0.75
    present
    -0.65
    Discussion
    -0.64
    rea
    -0.64
    erva
    -0.64
    vic
    -0.64
    raz
    -0.64
    ridor
    -0.62
    neum
    -0.62
    uid
    -0.62
    POSITIVE LOGITS
     mastering
    1.04
     mastery
    0.97
     mastered
    0.92
     skills
    0.91
     tricks
    0.81
     proficiency
    0.81
     techniques
    0.80
     patience
    0.80
     technique
    0.80
     tactics
    0.72
    Activations Density 0.029%

    No Known Activations