© 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. 1275
    Prev
    Next
    INDEX
    Explanations

    text related to legal matters and processes

    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
    640
    +0.31
    1.5%
    373
    +0.17
    0.8%
    442
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.31
    0.14
    107
    +0.17
    0.12
    442
    +0.14
    0.12
    Negative Logits
     neighb
    -0.93
     offended
    -0.77
     tram
    -0.74
     lifes
    -0.71
     prayers
    -0.71
     neigh
    -0.71
     detract
    -0.70
     skelet
    -0.69
     hers
    -0.69
     bloc
    -0.69
    POSITIVE LOGITS
    Firstly
    1.52
    Specifically
    1.50
    First
    1.49
    Overview
    1.48
    What
    1.46
    Why
    1.45
    Before
    1.45
    Consider
    1.45
    Here
    1.44
    Introduction
    1.41
    Activations Density 0.368%

    No Known Activations