© 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. 5486
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and science, such as waves, radiation, ionosphere, and communication methods

    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
    314
    +0.13
    0.6%
    373
    +0.13
    0.6%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.13
    0.06
    398
    +0.13
    0.05
    0
    +0.11
    0.05
    Negative Logits
    oldemort
    -0.63
    ichita
    -0.56
     referee
    -0.55
     upstairs
    -0.55
     backstage
    -0.54
    aults
    -0.54
    ault
    -0.54
     downstairs
    -0.53
    irt
    -0.52
    Fed
    -0.52
    POSITIVE LOGITS
    ²¾
    0.77
     its
    0.76
     related
    0.73
     other
    0.68
     therefore
    0.68
    other
    0.65
     consequently
    0.64
     associated
    0.63
    GAN
    0.62
    roph
    0.61
    Activations Density 0.330%

    No Known Activations