© 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. 20
    Prev
    Next
    INDEX
    Explanations

    phrases related to picking things up

    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
    213
    +0.11
    0.5%
    276
    +0.11
    0.5%
    349
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.11
    0.05
    25
    +0.11
    0.04
    433
    +0.10
    0.04
    Negative Logits
    CTV
    -0.82
    interrupted
    -0.70
    acion
    -0.65
    itement
    -0.64
    cess
    -0.64
     Spiegel
    -0.63
    Sea
    -0.63
    FB
    -0.62
    Goal
    -0.62
     TAG
    -0.61
    POSITIVE LOGITS
    pocket
    1.34
    axe
    1.24
    eting
    1.22
    eters
    1.12
    ety
    0.89
    ets
    0.88
    hots
    0.88
    aign
    0.86
    picking
    0.85
    eter
    0.84
    Activations Density 0.495%

    No Known Activations