© 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. 15923
    Prev
    Next
    INDEX
    Explanations

    topics related to self-reflection and personal growth

    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
    481
    +0.24
    1.1%
    447
    +0.13
    0.6%
    373
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.24
    0.04
    362
    +0.13
    0.05
    382
    +0.13
    0.03
    Negative Logits
     hemor
    -0.77
     enthusi
    -0.59
    RET
    -0.58
     barring
    -0.57
     theirs
    -0.56
     although
    -0.56
     Au
    -0.55
     millenn
    -0.54
     Palestin
    -0.52
     Presbyter
    -0.52
    POSITIVE LOGITS
     oneself
    0.80
     Yourself
    0.79
     entails
    0.75
     yourself
    0.74
    ctions
    0.69
    ealous
    0.69
    nikov
    0.69
     involves
    0.66
     Basics
    0.64
     requires
    0.64
    Activations Density 0.453%

    No Known Activations