© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 24576
    9. 8-RES_FS24576-JB
    11. 9021
    Prev
    Next
    INDEX
    Explanations

    programming-related terms or phrases

    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
    373
    +0.23
    1.1%
    481
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    661
    +0.23
    0.03
    183
    +0.11
    0.03
    267
    +0.10
    0.04
    Negative Logits
    SPONSORED
    -0.87
     âĢ¦"
    -0.67
     HOU
    -0.65
     ****
    -0.63
     pic
    -0.62
    âĢ¦."
    -0.58
     Antioch
    -0.57
    NR
    -0.57
     Baghdad
    -0.57
     Jr
    -0.56
    POSITIVE LOGITS
    withstanding
    0.76
     simplest
    0.75
    olars
    0.73
    resa
    0.72
    ynchronous
    0.71
    orically
    0.71
    ntil
    0.71
    iage
    0.70
    hester
    0.70
    rary
    0.69
    Activations Density 0.344%

    No Known Activations