© 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. 2603
    Prev
    Next
    INDEX
    Explanations

    locations or events related to current affairs

    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
    210
    +0.10
    0.5%
    454
    +0.10
    0.4%
    397
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.05
    659
    +0.10
    0.04
    284
    +0.10
    0.03
    Negative Logits
     cerebral
    -0.71
     ze
    -0.67
     DRAG
    -0.67
     indo
    -0.67
     clicks
    -0.66
     ray
    -0.66
     ammunition
    -0.66
    phal
    -0.65
     confir
    -0.65
    chnology
    -0.64
    POSITIVE LOGITS
    iv
    1.05
    IV
    0.94
    iva
    0.92
    ival
    0.92
    ivism
    0.91
     Collective
    0.90
    osi
    0.89
    Ĥª
    0.86
    ivist
    0.86
    ieft
    0.85
    Activations Density 0.222%

    No Known Activations