© 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. 8144
    Prev
    Next
    INDEX
    Explanations

    instructions related to completing a task or a process

    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
    +0.11
    0.5%
    406
    +0.11
    0.5%
    756
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.11
    0.08
    351
    +0.11
    0.03
    406
    +0.11
    0.04
    Negative Logits
     declass
    -0.84
     canon
    -0.80
     Chomsky
    -0.77
    zsche
    -0.71
     eluc
    -0.71
     anthrop
    -0.70
     archaeological
    -0.70
     Reconstruction
    -0.70
    Gameplay
    -0.69
     Anthropology
    -0.69
    POSITIVE LOGITS
     buyers
    1.40
     buyer
    1.36
     payment
    1.34
     priced
    1.29
     coupon
    1.28
     purchaser
    1.28
     cheapest
    1.27
     seller
    1.26
     customers
    1.26
     purchases
    1.25
    Activations Density 0.825%

    No Known Activations