© 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. 19537
    Prev
    Next
    INDEX
    Explanations

    future tense actions

    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
    +0.15
    0.7%
    95
    +0.11
    0.5%
    107
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.15
    0.06
    95
    +0.11
    0.04
    551
    +0.11
    0.05
    Negative Logits
    quickShipAvailable
    -0.66
     constituted
    -0.60
     debilitating
    -0.59
    licted
    -0.59
    Creat
    -0.57
    pires
    -0.56
     Measures
    -0.56
     soaring
    -0.56
     Initiative
    -0.55
    ategory
    -0.55
    POSITIVE LOGITS
     gladly
    1.36
     continue
    1.06
     endeavour
    1.04
     be
    1.02
     ende
    0.94
    iam
    0.94
     NEVER
    0.94
     definitely
    0.93
     strive
    0.92
     try
    0.92
    Activations Density 0.124%

    No Known Activations