© 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. 5265
    Prev
    Next
    INDEX
    Explanations

    verbs related to thoughts, beliefs, and actions

    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
    49
    +0.12
    0.6%
    566
    +0.11
    0.5%
    615
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.12
    0.07
    566
    +0.11
    0.05
    551
    +0.10
    0.05
    Negative Logits
     backdrop
    -0.69
    quickShipAvailable
    -0.69
     Shots
    -0.68
    idelines
    -0.64
     Beyond
    -0.62
     dynamics
    -0.61
     offsets
    -0.60
    Scale
    -0.60
     Apart
    -0.59
    EMS
    -0.59
    POSITIVE LOGITS
     lose
    1.16
     succeed
    1.02
     get
    0.99
     someday
    0.99
     hear
    0.96
     find
    0.93
     offend
    0.93
     starve
    0.92
     regain
    0.92
     spend
    0.91
    Activations Density 0.241%

    No Known Activations