© 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. 8890
    Prev
    Next
    INDEX
    Explanations

    references to specific names or places

    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
    677
    +0.11
    0.5%
    470
    +0.10
    0.5%
    250
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.04
    392
    +0.10
    0.03
    659
    +0.10
    0.03
    Negative Logits
    inventoryQuantity
    -0.81
     Contra
    -0.78
     defic
    -0.77
    soType
    -0.73
     contrace
    -0.73
     Fairfax
    -0.72
     dilig
    -0.71
     confir
    -0.70
     indecent
    -0.70
    uyomi
    -0.69
    POSITIVE LOGITS
    k
    1.45
    K
    1.36
    ks
    1.35
    kt
    1.31
    KC
    1.27
    ked
    1.26
    king
    1.24
    kan
    1.23
    KS
    1.21
    KE
    1.19
    Activations Density 0.131%

    No Known Activations