© 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 EvalsExportsAPI 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. 12341
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and self-reflection, focusing on emotional aspects and introspection

    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
    87
    +0.35
    1.9%
    762
    +0.13
    0.7%
    526
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.35
    -0.02
    762
    +0.13
    0.10
    526
    +0.11
    0.00
    Negative Logits
    DragonMagazine
    -0.68
    ircraft
    -0.62
    atform
    -0.58
    ateur
    -0.58
    nsic
    -0.56
    classified
    -0.56
    bats
    -0.56
    sites
    -0.56
    isbury
    -0.56
    cedented
    -0.55
    POSITIVE LOGITS
     unworthy
    0.83
     righteousness
    0.82
     sinful
    0.81
     injust
    0.79
     selfish
    0.79
     oneself
    0.78
     selves
    0.78
     oppress
    0.77
     oppression
    0.76
     eternity
    0.75
    Activations Density 0.966%

    No Known Activations