© 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. 11945
    Prev
    Next
    INDEX
    Explanations

    phrases related to reflections on the world and human potential

    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
    288
    +0.10
    0.4%
    377
    +0.09
    0.4%
    544
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    558
    +0.10
    0.03
    651
    +0.09
    0.04
    203
    +0.08
    0.03
    Negative Logits
    ippi
    -0.94
    imon
    -0.86
     actionGroup
    -0.83
    veyard
    -0.83
    sbm
    -0.78
    IFF
    -0.72
    ¿½
    -0.72
    ifer
    -0.71
    drawn
    -0.70
    ++++
    -0.68
    POSITIVE LOGITS
    liness
    1.00
    building
    0.88
    wide
    0.86
    scape
    0.85
    osphere
    0.81
     revolves
    0.81
     economy
    0.79
     premiere
    0.78
    eers
    0.75
    wake
    0.73
    Activations Density 0.057%

    No Known Activations