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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11631
    Prev
    Next
    INDEX
    Explanations

    statistical gaming terminology

    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
    480
    +0.48
    2.7%
    118
    +0.09
    0.5%
    266
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.48
    0.00
    314
    +0.09
    -0.01
    266
    +0.08
    0.08
    Negative Logits
     acad
    -0.60
     Jaguar
    -0.57
     disbanded
    -0.56
     nicknamed
    -0.55
     coordinator
    -0.54
     nutshell
    -0.54
     convened
    -0.52
     Tracker
    -0.51
    soDeliveryDate
    -0.51
     pioneered
    -0.51
    POSITIVE LOGITS
    damage
    0.78
    sic
    0.75
    plet
    0.69
    verage
    0.67
    ptoms
    0.67
    distance
    0.67
    arranted
    0.67
    lethal
    0.67
    alien
    0.66
    abilities
    0.66
    Activations Density 0.795%

    No Known Activations