© 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 12288
    9. 8-RES_FS12288-JB
    11. 10665
    Prev
    Next
    INDEX
    Explanations

    information related to organizations, programs, and initiatives, particularly focusing on their establishment and purpose

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    679
    +0.11
    0.5%
    723
    +0.10
    0.5%
    278
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.11
    0.06
    723
    +0.10
    0.05
    278
    +0.10
    0.04
    Negative Logits
     nausea
    -0.90
     hardness
    -0.85
     strokes
    -0.77
     Ashes
    -0.75
     curves
    -0.75
     torped
    -0.75
     spoil
    -0.74
    damage
    -0.73
     delays
    -0.73
     gunshots
    -0.71
    POSITIVE LOGITS
     headquartered
    1.26
     affiliated
    1.24
     disbanded
    1.24
     staffed
    1.22
     nonpartisan
    1.19
    affiliated
    1.17
    ederation
    1.12
     nonprofit
    1.11
     501
    1.11
     chaired
    1.11
    Activations Density 1.134%

    No Known Activations