© 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. 10944
    Prev
    Next
    INDEX
    Explanations

    information related to public health and social disparities

    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
    756
    +0.17
    0.8%
    481
    +0.13
    0.6%
    697
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.17
    -0.01
    655
    +0.13
    0.05
    724
    +0.10
    0.06
    Negative Logits
     airs
    -0.69
    agents
    -0.68
    craft
    -0.68
     Fancy
    -0.67
     prank
    -0.67
     microphones
    -0.66
     voic
    -0.64
     translator
    -0.64
    poke
    -0.64
     Toro
    -0.63
    POSITIVE LOGITS
     declines
    1.18
     decrease
    1.17
     decreases
    1.14
     decreasing
    1.14
     decreased
    1.13
     declining
    1.11
    Decre
    1.10
     unemployment
    1.06
     steadily
    1.06
     decline
    1.05
    Activations Density 0.663%

    No Known Activations