© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5713
    Prev
    Next
    INDEX
    Explanations

    specific dates and events

    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
    393
    +0.18
    0.9%
    362
    +0.13
    0.6%
    606
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.18
    0.07
    636
    +0.13
    0.05
    393
    +0.12
    0.05
    Negative Logits
    rete
    -0.76
    SPONSORED
    -0.73
    £ı
    -0.71
    rade
    -0.70
    gae
    -0.70
    chan
    -0.68
    hops
    -0.66
    flows
    -0.65
    ucl
    -0.65
    gru
    -0.64
    POSITIVE LOGITS
     same
    1.13
     slightest
    1.10
     entirety
    1.05
     coveted
    1.04
     latter
    1.01
     presidency
    1.00
     remainder
    0.99
     reins
    0.99
     mantle
    0.98
     largest
    0.95
    Activations Density 0.219%

    No Known Activations