© 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. 1120
    Prev
    Next
    INDEX
    Explanations

    food items and descriptive terms related to food

    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
    +0.13
    0.6%
    183
    +0.12
    0.5%
    220
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.13
    0.14
    693
    +0.12
    0.13
    220
    +0.11
    0.12
    Negative Logits
    atem
    -0.75
    orc
    -0.69
    etsk
    -0.67
    plin
    -0.63
    orem
    -0.63
    atis
    -0.62
     forgiven
    -0.60
     shake
    -0.59
    rolet
    -0.58
    amaru
    -0.58
    POSITIVE LOGITS
    th
    1.36
    61
    1.16
    87
    1.16
    81
    1.16
    92
    1.15
    06
    1.14
    91
    1.14
    84
    1.14
    71
    1.13
    00
    1.13
    Activations Density 0.863%

    No Known Activations