Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 1034
    Prev
    Next
    INDEX
    Explanations

    names of people or entities

    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
    603
    +0.11
    0.5%
    430
    +0.11
    0.5%
    129
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.11
    0.07
    653
    +0.11
    0.06
    129
    +0.10
    0.06
    Negative Logits
    EMS
    -0.79
    yrinth
    -0.72
    romy
    -0.72
    iasm
    -0.71
    icult
    -0.68
    aunders
    -0.68
    iths
    -0.68
    istar
    -0.67
    psey
    -0.65
    nuts
    -0.65
    POSITIVE LOGITS
    plates
    1.44
    plate
    1.29
    paces
    1.07
     redacted
    0.94
    names
    0.94
     tag
    0.94
     tags
    0.93
    ames
    0.91
     names
    0.88
     recognition
    0.88
    Activations Density 1.975%

    No Known Activations