© 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 3072
    9. 8-RES_FS3072-JB
    11. 221
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to storage devices and data management

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    67
    +0.11
    0.5%
    559
    +0.10
    0.5%
    589
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.11
    0.09
    67
    +0.10
    0.08
    238
    +0.09
    0.07
    Negative Logits
    etsk
    -0.65
    opic
    -0.63
     fielder
    -0.62
    qual
    -0.61
     enh
    -0.60
    SPONSORED
    -0.59
    ãģĨ
    -0.58
    apego
    -0.57
    izing
    -0.56
     bona
    -0.56
    POSITIVE LOGITS
    bps
    0.87
    hz
    0.81
     increments
    0.80
    undred
    0.80
     Ago
    0.73
     apiece
    0.72
    renheit
    0.69
    illion
    0.69
     olds
    0.69
    IU
    0.69
    Activations Density 1.094%

    No Known Activations