© 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. 20616
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and figures

    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
    650
    +0.13
    0.6%
    314
    +0.13
    0.6%
    675
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    650
    +0.13
    0.08
    675
    +0.13
    0.08
    584
    +0.09
    0.06
    Negative Logits
     reflex
    -0.76
     lapse
    -0.70
     peripheral
    -0.68
     apes
    -0.66
     pigeon
    -0.66
     disadvantage
    -0.66
     intersections
    -0.64
    matic
    -0.63
     synerg
    -0.62
     advantageous
    -0.61
    POSITIVE LOGITS
    ï¸ı
    1.26
    âĶĢâĶĢ
    0.87
    ever
    0.82
    âĶĢâĶĢâĶĢâĶĢ
    0.81
    uthor
    0.81
    arthed
    0.78
    _>
    0.77
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.76
    ternity
    0.76
    IELD
    0.76
    Activations Density 0.142%

    No Known Activations