© 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. 11828
    Prev
    Next
    INDEX
    Explanations

    names of individuals and organizations, particularly in a Spanish-speaking context

    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
    534
    +0.10
    0.4%
    648
    +0.10
    0.4%
    752
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.05
    232
    +0.10
    0.05
    701
    +0.09
    0.04
    Negative Logits
    toe
    -0.77
    worms
    -0.77
     arrows
    -0.76
    inventoryQuantity
    -0.75
    rouse
    -0.72
     ankles
    -0.70
     toes
    -0.70
    ellow
    -0.70
     wallets
    -0.70
     tears
    -0.69
    POSITIVE LOGITS
     Univers
    1.08
     Ré
    1.08
     Instit
    1.06
     Portug
    1.03
     Franç
    1.00
     Mé
    0.99
     Agric
    0.98
     Catal
    0.98
     Libre
    0.95
     pour
    0.94
    Activations Density 0.141%

    No Known Activations