© 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. 8705
    Prev
    Next
    INDEX
    Explanations

    phrases related to effort and determination

    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
    745
    +0.14
    0.6%
    131
    +0.11
    0.5%
    450
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    738
    +0.14
    0.01
    78
    +0.11
    0.01
    767
    +0.10
    0.01
    Negative Logits
     concerns
    -0.68
    \">
    -0.66
    aca
    -0.66
     Concern
    -0.66
    \-
    -0.64
    SOURCE
    -0.64
     concern
    -0.62
    ablishment
    -0.61
    RIP
    -0.60
    ufact
    -0.60
    POSITIVE LOGITS
     unsuccessfully
    0.98
     harder
    0.96
     hardest
    0.92
     luck
    0.89
     trick
    0.84
     vain
    0.83
     experiment
    0.83
     patience
    0.74
    uden
    0.70
     futile
    0.70
    Activations Density 0.073%

    No Known Activations