© 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. 6632
    Prev
    Next
    INDEX
    Explanations

    positive qualities related to individuals such as nature, complementing skills, courage, infectious enthusiasm, and appreciated qualities

    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
    230
    +0.15
    0.7%
    540
    +0.11
    0.5%
    724
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.15
    0.07
    512
    +0.11
    0.05
    490
    +0.11
    0.05
    Negative Logits
    iatus
    -0.89
    dule
    -0.79
     Emails
    -0.75
    hops
    -0.70
    von
    -0.67
     Discussion
    -0.66
     Procedures
    -0.66
    heid
    -0.65
    leases
    -0.64
    IDs
    -0.64
    POSITIVE LOGITS
     unmatched
    1.04
     accent
    1.01
     infectious
    0.98
     qualities
    0.97
     underpin
    0.96
     contagious
    0.95
     undeniable
    0.94
     tempered
    0.94
     rewarded
    0.93
     trait
    0.93
    Activations Density 0.578%

    No Known Activations