© 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. 8136
    Prev
    Next
    INDEX
    Explanations

    phrases related to the usage of resources or systems in specific contexts

    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
    665
    +0.12
    0.5%
    420
    +0.11
    0.5%
    554
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.12
    0.04
    665
    +0.11
    0.04
    554
    +0.11
    0.02
    Negative Logits
     Hai
    -0.75
    bitious
    -0.65
     Roose
    -0.65
    nesty
    -0.59
     Vie
    -0.57
    alos
    -0.56
     Bravo
    -0.56
    Heart
    -0.56
    dom
    -0.55
     Pis
    -0.55
    POSITIVE LOGITS
     sparing
    1.20
    fully
    0.94
     interchange
    0.90
     wisely
    0.82
     extensively
    0.82
    pez
    0.80
     exclusively
    0.79
    ragon
    0.76
    FUL
    0.75
     efficiently
    0.75
    Activations Density 0.066%

    No Known Activations