© 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 EvalsExportsinterp-engineNEWAPI 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. 4690
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic market analysis, price, and regulations

    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
    68
    +0.13
    0.6%
    362
    +0.13
    0.6%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.13
    0.07
    67
    +0.13
    0.06
    362
    +0.11
    0.07
    Negative Logits
    undrum
    -0.81
    achu
    -0.81
    emark
    -0.80
    hander
    -0.80
    ortium
    -0.80
     tremend
    -0.78
    ittee
    -0.78
    keleton
    -0.76
    ouf
    -0.75
    adder
    -0.75
    POSITIVE LOGITS
     scenarios
    1.20
     environments
    1.19
     versions
    1.18
     situations
    1.14
     alternatives
    1.10
     groups
    1.08
     areas
    1.07
     models
    1.07
     structures
    1.06
     architectures
    1.06
    Activations Density 0.373%

    No Known Activations