© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18486
    Prev
    Next
    INDEX
    Explanations

    people's names related to music, entertainment, or sports

    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
    314
    +0.14
    0.6%
    347
    +0.11
    0.5%
    549
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.14
    0.01
    316
    +0.11
    0.01
    289
    +0.09
    0.01
    Negative Logits
    perse
    -0.67
    pires
    -0.59
    ISSION
    -0.59
    bourg
    -0.58
    xia
    -0.58
    avorite
    -0.56
     overriding
    -0.56
    naires
    -0.56
    jri
    -0.56
     standardized
    -0.55
    POSITIVE LOGITS
    tered
    1.07
    avia
    1.02
    room
    1.00
    allion
    0.96
    rooms
    0.93
    girl
    0.92
    chet
    0.91
    ista
    0.91
    ting
    0.89
    kid
    0.88
    Activations Density 0.013%

    No Known Activations