© 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. 6473
    Prev
    Next
    INDEX
    Explanations

    phrases related to boundaries and ethical conduct

    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
    583
    +0.12
    0.6%
    737
    +0.12
    0.5%
    594
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.12
    0.05
    583
    +0.12
    0.04
    128
    +0.10
    0.04
    Negative Logits
    FactoryReloaded
    -0.85
    soDeliveryDate
    -0.85
    USS
    -0.84
     Cosponsors
    -0.84
    dit
    -0.79
    antically
    -0.76
    ODUCT
    -0.75
     enthusi
    -0.75
    recent
    -0.75
    mittedly
    -0.73
    POSITIVE LOGITS
     swe
    0.85
     losers
    0.84
     Sacrifice
    0.77
     equals
    0.73
     ain
    0.73
     evil
    0.72
     Pharaoh
    0.72
     sinners
    0.72
     Happiness
    0.71
     darkness
    0.71
    Activations Density 0.525%

    No Known Activations