© 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. 4294
    Prev
    Next
    INDEX
    Explanations

    names or surnames related to individuals

    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
    659
    +0.20
    1.0%
    447
    +0.17
    0.8%
    511
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.20
    0.12
    232
    +0.17
    0.07
    511
    +0.11
    0.07
    Negative Logits
    âĶĢâĶĢ
    -0.78
    SPONSORED
    -0.76
    ··
    -0.75
     accordingly
    -0.69
     underwater
    -0.67
     logically
    -0.65
     respectively
    -0.65
     governing
    -0.64
     constant
    -0.64
    etheless
    -0.63
    POSITIVE LOGITS
    verson
    1.04
    linger
    1.03
    ley
    1.00
    ahl
    1.00
    atz
    0.99
    lett
    0.99
    lund
    0.98
    isson
    0.97
    gaard
    0.96
    enberg
    0.95
    Activations Density 0.237%

    No Known Activations