© 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. 8622
    Prev
    Next
    INDEX
    Explanations

    tech-related terms and product names

    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
    447
    +0.22
    1.0%
    481
    +0.12
    0.5%
    712
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.07
    24
    +0.12
    0.05
    537
    +0.12
    0.05
    Negative Logits
    azeera
    -0.78
     inclined
    -0.76
    aples
    -0.73
    >[
    -0.73
     parity
    -0.69
     abst
    -0.68
     waning
    -0.68
    anwhile
    -0.67
    uchin
    -0.65
    depending
    -0.65
    POSITIVE LOGITS
    âĦ¢
    0.95
    Plugin
    0.92
     Ltd
    0.92
     Association
    0.90
     Calculator
    0.90
     Plugin
    0.89
     LLC
    0.89
     Contest
    0.86
     Competition
    0.85
    Provider
    0.85
    Activations Density 0.357%

    No Known Activations