© 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. 19510
    Prev
    Next
    INDEX
    Explanations

    phrases related to awards and recognition

    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
    274
    +0.16
    0.7%
    638
    +0.12
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.16
    0.03
    234
    +0.12
    0.02
    717
    +0.11
    0.02
    Negative Logits
    ohyd
    -0.70
    vironment
    -0.66
    ierre
    -0.66
    ths
    -0.65
     Anon
    -0.60
     Stur
    -0.60
     Armed
    -0.59
     Geo
    -0.59
     Steps
    -0.59
     Ange
    -0.59
    POSITIVE LOGITS
     awards
    1.05
     awarded
    1.04
     winner
    1.02
    winning
    1.02
     laure
    1.01
     nominations
    1.00
     winners
    1.00
     prizes
    0.99
    Winner
    0.99
    winner
    0.95
    Activations Density 0.024%

    No Known Activations