© 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. 6631
    Prev
    Next
    INDEX
    Explanations

    phrases related to pride and fighting for a cause

    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
    684
    +0.10
    0.4%
    762
    +0.10
    0.4%
    564
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    693
    +0.10
    0.02
    99
    +0.10
    0.02
    404
    +0.09
    0.02
    Negative Logits
    ional
    -0.96
    ivia
    -0.91
    orius
    -0.90
    iments
    -0.89
    anson
    -0.89
    wana
    -0.88
    gins
    -0.84
    URE
    -0.83
    ION
    -0.83
    ulus
    -0.82
    POSITIVE LOGITS
     attractions
    0.86
     attraction
    0.78
     amen
    0.77
     hospitality
    0.76
     kios
    0.75
     apartment
    0.73
     apartments
    0.73
     resorts
    0.73
     corner
    0.72
     retreat
    0.72
    Activations Density 0.081%

    No Known Activations