© 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. 20809
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and engineering

    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
    +0.18
    0.9%
    447
    +0.16
    0.8%
    481
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.18
    0.09
    362
    +0.16
    0.09
    393
    +0.15
    0.08
    Negative Logits
    SPONSORED
    -0.74
    leground
    -0.71
    Scotland
    -0.69
    ceans
    -0.68
    AIDS
    -0.67
    .''
    -0.67
    —-
    -0.66
    Advertisement
    -0.65
    Malley
    -0.65
    poke
    -0.64
    POSITIVE LOGITS
    oret
    1.65
     simplest
    1.43
     easiest
    1.37
     resultant
    1.17
     earliest
    1.15
     downside
    1.14
     remainder
    1.13
     following
    1.12
     resulting
    1.11
    orem
    1.11
    Activations Density 0.425%

    No Known Activations