© 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 1536
    9. 8-RES_FS1536-JB
    11. 1095
    Prev
    Next
    INDEX
    Explanations

    political and ethical terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    314
    +0.21
    1.0%
    499
    +0.10
    0.5%
    433
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.21
    -0.01
    331
    +0.10
    0.09
    499
    +0.10
    0.07
    Negative Logits
     Weston
    -0.68
     Reef
    -0.64
     Allied
    -0.61
     Constantin
    -0.55
     Parkinson
    -0.54
     Laz
    -0.53
     garden
    -0.52
     Vita
    -0.52
     AFL
    -0.52
     Lyme
    -0.52
    POSITIVE LOGITS
    É
    0.98
    vernment
    0.98
    mosp
    0.92
    estine
    0.90
    [/
    0.90
    lihood
    0.89
    theless
    0.89
    Í
    0.84
    ]=
    0.83
    */(
    0.82
    Activations Density 3.527%

    No Known Activations