© 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. 7970
    Prev
    Next
    INDEX
    Explanations

    phrases related to translation and language

    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
    18
    +0.10
    0.5%
    301
    +0.10
    0.5%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.10
    0.02
    18
    +0.10
    0.02
    733
    +0.10
    0.01
    Negative Logits
    ndra
    -0.91
    achine
    -0.81
    --+
    -0.81
     Gamble
    -0.78
    oeuv
    -0.73
    pton
    -0.72
    ramid
    -0.69
    appiness
    -0.69
    pload
    -0.68
    sbm
    -0.68
    POSITIVE LOGITS
     translation
    1.16
     translations
    1.11
     transl
    1.04
     translator
    1.02
     subtitles
    1.00
     Translation
    0.97
    translation
    0.97
     interpre
    0.89
     translated
    0.89
     interpreter
    0.88
    Activations Density 0.023%

    No Known Activations