© 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. 10042
    Prev
    Next
    INDEX
    Explanations

    names of social media or internet platforms

    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
    314
    +0.12
    0.5%
    437
    +0.10
    0.5%
    537
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.12
    0.02
    537
    +0.10
    0.02
    1
    +0.10
    0.02
    Negative Logits
    cheat
    -0.72
    steen
    -0.67
    gery
    -0.63
    adish
    -0.62
    Ħ¢
    -0.61
     Leaves
    -0.61
     restraining
    -0.57
     Refuge
    -0.56
    fare
    -0.56
    VL
    -0.56
    POSITIVE LOGITS
    icut
    1.34
     dots
    1.01
    ivity
    0.94
    ioned
    0.90
    links
    0.85
    ions
    0.84
    ications
    0.83
    nect
    0.82
    anooga
    0.81
     wire
    0.80
    Activations Density 0.029%

    No Known Activations