© 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. 20799
    Prev
    Next
    INDEX
    Explanations

    issues related to justice, fairness, governance, and transparency in various societal and political contexts

    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
    496
    +0.16
    0.7%
    314
    +0.14
    0.6%
    447
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.16
    0.07
    333
    +0.14
    0.06
    697
    +0.13
    0.05
    Negative Logits
     reflex
    -0.91
     favor
    -0.82
     favour
    -0.80
     shape
    -0.76
     synerg
    -0.75
     morph
    -0.75
     domest
    -0.74
     pri
    -0.73
     intu
    -0.71
     graz
    -0.71
    POSITIVE LOGITS
    ccording
    1.25
    ï¸ı
    1.24
    Because
    1.12
    There
    1.05
    It
    1.05
    Originally
    1.03
    These
    1.01
    This
    1.00
    Lastly
    1.00
    If
    0.99
    Activations Density 0.114%

    No Known Activations