© 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 1536
    9. 8-RES_FS1536-JB
    11. 1116
    Prev
    Next
    INDEX
    Explanations

    references to support for various causes, initiatives, or individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    +0.14
    0.7%
    288
    +0.14
    0.7%
    459
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.12
    225
    +0.14
    0.09
    679
    +0.11
    0.10
    Negative Logits
    apeake
    -0.71
    tein
    -0.69
    ãĥ£
    -0.64
     sweat
    -0.62
     alarm
    -0.61
     Hebdo
    -0.60
    selves
    -0.60
    ilus
    -0.58
     burg
    -0.58
    oshop
    -0.58
    POSITIVE LOGITS
    arity
    0.87
    ament
    0.86
    heses
    0.80
    itism
    0.77
    Support
    0.72
    ances
    0.71
     Supports
    0.70
     Vector
    0.69
     afforded
    0.69
    ancing
    0.69
    Activations Density 1.959%

    No Known Activations