© 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. 8618
    Prev
    Next
    INDEX
    Explanations

    Twitter handles

    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
    +0.17
    0.8%
    238
    +0.11
    0.5%
    697
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.17
    0.05
    314
    +0.11
    0.01
    659
    +0.11
    0.04
    Negative Logits
     Direction
    -0.91
     Parish
    -0.88
     Versus
    -0.86
     Demand
    -0.85
     Tone
    -0.85
     Stretch
    -0.83
     Quality
    -0.83
     Address
    -0.83
     Supply
    -0.80
     Kut
    -0.80
    POSITIVE LOGITS
    podcast
    1.11
    obal
    1.10
    aylor
    1.09
    raham
    1.09
    erc
    1.09
    music
    1.07
    imore
    1.07
    iverpool
    1.05
    idth
    1.04
    eworks
    1.04
    Activations Density 0.116%

    No Known Activations