© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 18599
    Prev
    Next
    INDEX
    Explanations

    proper names related to legal matters

    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
    53
    +0.12
    0.5%
    189
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.12
    0.01
    53
    +0.11
    0.01
    392
    +0.11
    0.01
    Negative Logits
    yrinth
    -0.91
    olulu
    -0.82
    iries
    -0.77
    sie
    -0.76
    irie
    -0.75
    undai
    -0.74
     Gutenberg
    -0.74
    ouri
    -0.69
    ORE
    -0.69
    arine
    -0.69
    POSITIVE LOGITS
    igham
    0.81
    backer
    0.74
    abl
    0.74
     Campaign
    0.72
    butt
    0.69
    stein
    0.67
    ichick
    0.66
    ubi
    0.65
     Injury
    0.65
     Quinn
    0.65
    Activations Density 0.026%

    No Known Activations