© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 12075
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to software development

    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
    447
    +0.14
    0.6%
    715
    +0.13
    0.6%
    566
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.14
    0.08
    49
    +0.13
    0.08
    718
    +0.11
    0.07
    Negative Logits
     Sacramento
    -0.70
     Friendship
    -0.70
     Tomorrow
    -0.68
     Cancer
    -0.68
     Worth
    -0.68
    justice
    -0.67
     Society
    -0.67
     America
    -0.66
     Kinder
    -0.65
     taxp
    -0.65
    POSITIVE LOGITS
     specify
    1.17
     calculate
    1.14
     manually
    1.09
     optimize
    1.09
     allocate
    1.09
     utilize
    1.09
     create
    1.06
     omit
    1.05
     assign
    1.05
     iter
    1.05
    Activations Density 0.455%

    No Known Activations