© 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. 1327
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Diane Rodham" in the text

    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
    223
    +0.10
    0.5%
    229
    +0.10
    0.5%
    350
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.10
    0.01
    325
    +0.10
    0.01
    645
    +0.10
    0.01
    Negative Logits
    ters
    -0.77
    PDATE
    -0.73
    mare
    -0.72
    aic
    -0.70
    KT
    -0.68
    fect
    -0.67
    bidden
    -0.67
    tered
    -0.67
    eu
    -0.64
    ELL
    -0.64
    POSITIVE LOGITS
     Rodham
    1.16
     Clinton
    1.10
    clinton
    0.96
     Clintons
    0.89
     Abedin
    0.84
    Clinton
    0.81
    INTON
    0.79
    umenthal
    0.76
     aide
    0.75
    velt
    0.74
    Activations Density 0.023%

    No Known Activations