© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    words related to governmental policies and procedures

    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
    +0.15
    0.7%
    53
    +0.09
    0.4%
    508
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.15
    0.10
    537
    +0.09
    0.11
    147
    +0.09
    0.08
    Negative Logits
     oranges
    -0.91
     Balls
    -0.75
    aterasu
    -0.72
     Hera
    -0.70
     peppers
    -0.70
     Tears
    -0.69
     TAMADRA
    -0.69
    oldemort
    -0.69
     swe
    -0.67
     Dracula
    -0.66
    POSITIVE LOGITS
     occupational
    0.89
     allied
    0.88
    technical
    0.88
    sonian
    0.88
     aerospace
    0.88
     environmental
    0.82
     interpersonal
    0.81
    ultural
    0.81
    ural
    0.81
    chemical
    0.79
    Activations Density 2.036%

    No Known Activations