© 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. 10985
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning specific locations and military activities in current events

    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
    393
    +0.15
    0.7%
    362
    +0.14
    0.7%
    127
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.09
    636
    +0.14
    0.06
    385
    +0.14
    0.06
    Negative Logits
    ea
    -0.77
    abel
    -0.73
    atoon
    -0.72
    venture
    -0.72
    utan
    -0.71
    milo
    -0.71
    nell
    -0.70
    ettings
    -0.70
    emption
    -0.69
    isson
    -0.69
    POSITIVE LOGITS
     entire
    1.18
     hardest
    1.05
     unsuspecting
    1.02
     weakest
    1.00
     poorest
    1.00
     nation
    0.99
     slightest
    0.94
     same
    0.94
     Clintons
    0.93
     entirety
    0.93
    Activations Density 0.296%

    No Known Activations