© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 22021
    Prev
    Next
    INDEX
    Explanations

    names of individuals, especially in political contexts

    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
    481
    +0.34
    1.7%
    416
    +0.12
    0.6%
    378
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.34
    0.08
    341
    +0.12
    0.04
    415
    +0.11
    0.04
    Negative Logits
     Poverty
    -0.66
     Fib
    -0.65
     Problems
    -0.64
     dams
    -0.64
    ictionary
    -0.64
    onz
    -0.63
     Fraud
    -0.62
     euph
    -0.62
     Wealth
    -0.62
     panic
    -0.61
    POSITIVE LOGITS
     exempted
    0.88
     participating
    0.88
     inclusion
    0.83
     boarded
    0.82
    osta
    0.82
     attend
    0.81
    assad
    0.81
     participate
    0.79
     attending
    0.79
     departing
    0.79
    Activations Density 0.883%

    No Known Activations