© 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 49152
    5. 8-RES_FS49152-JB
    6. 37559
    Prev
    Next
    INDEX
    Explanations

    expressions of command or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.21
    1.0%
    442
    +0.11
    0.5%
    372
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    759
    +0.21
    0.02
    442
    +0.11
    0.02
    514
    +0.11
    0.02
    Negative Logits
     ABE
    -0.94
     TOP
    -0.77
     behav
    -0.75
     ozone
    -0.74
     Empires
    -0.74
     soup
    -0.74
     Antar
    -0.74
     Tanz
    -0.72
     cottage
    -0.72
     ZIP
    -0.71
    POSITIVE LOGITS
    ll
    1.56
    rh
    1.11
    ept
    1.10
    ill
    1.09
    ilty
    1.07
    shall
    1.06
    ple
    1.06
    vest
    1.06
    pled
    1.06
    ve
    1.05
    Activations Density 0.017%

    No Known Activations