© 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. 8828
    Prev
    Next
    INDEX
    Explanations

    keywords related to different topics such as sports, military, community, media, health, government, and politics

    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
    226
    +0.11
    0.5%
    301
    +0.09
    0.4%
    219
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.06
    18
    +0.09
    0.04
    575
    +0.09
    0.05
    Negative Logits
     himself
    -0.91
     herself
    -0.87
    tein
    -0.80
     oneself
    -0.72
     themselves
    -0.68
     Himself
    -0.67
    nikov
    -0.65
    auri
    -0.65
     Stern
    -0.62
     EntityItem
    -0.60
    POSITIVE LOGITS
     selves
    1.18
     ancestors
    1.00
     asses
    0.92
     counterparts
    0.89
     brethren
    0.87
     ourselves
    0.86
     partners
    0.81
     overl
    0.79
     cousins
    0.78
     motto
    0.76
    Activations Density 0.264%

    No Known Activations