© 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. 12260
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to data analysis and modeling

    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
    195
    +0.13
    0.6%
    160
    +0.12
    0.6%
    409
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.13
    0.02
    288
    +0.12
    0.02
    365
    +0.12
    0.01
    Negative Logits
    ittee
    -0.81
    flies
    -0.77
    reon
    -0.76
    ubs
    -0.76
    lehem
    -0.73
    akura
    -0.73
    arnaev
    -0.72
    bourg
    -0.72
    cham
    -0.72
    aples
    -0.71
    POSITIVE LOGITS
    ity
    1.37
    ized
    1.25
    ities
    1.24
    izable
    1.21
    ization
    1.21
    izes
    0.99
    izing
    0.98
     algebra
    0.97
    ITY
    0.94
     traject
    0.93
    Activations Density 0.033%

    No Known Activations