© 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 EvalsExportsinterp-engineNEWAPI 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. 21196
    Prev
    Next
    INDEX
    Explanations

    phrases related to morning routines and events, such as actions, habits, and events that commonly occur in the morning

    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
    594
    +0.10
    0.5%
    488
    +0.10
    0.4%
    436
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    594
    +0.10
    0.03
    662
    +0.10
    0.03
    115
    +0.09
    0.03
    Negative Logits
    ignty
    -0.93
    adr
    -0.91
    leased
    -0.84
    uador
    -0.83
    xon
    -0.82
    aws
    -0.81
    rity
    -0.80
    ords
    -0.79
    orius
    -0.79
    ilage
    -0.77
    POSITIVE LOGITS
     stroll
    1.01
     meal
    1.00
     snack
    1.00
     commute
    0.98
     routine
    0.97
     mornings
    0.96
     session
    0.94
     sunrise
    0.92
     breakfast
    0.92
     lunch
    0.90
    Activations Density 0.082%

    No Known Activations