© 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. 11067
    Prev
    Next
    INDEX
    Explanations

    words related to selfishness, particularly in personal relationships and decision-making 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
    635
    +0.11
    0.5%
    381
    +0.10
    0.5%
    191
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.11
    0.03
    288
    +0.10
    0.03
    151
    +0.09
    0.03
    Negative Logits
    Downloadha
    -0.80
    ICAN
    -0.75
    ournals
    -0.71
    enegger
    -0.69
    oval
    -0.69
    stable
    -0.68
    ahead
    -0.68
    accompanied
    -0.67
    interrupted
    -0.67
    aster
    -0.67
    POSITIVE LOGITS
     greed
    1.07
     motives
    0.91
     narciss
    0.90
     jealousy
    0.89
     greedy
    0.87
     jealous
    0.87
     arrogance
    0.87
     hypocrisy
    0.87
     hypoc
    0.87
     narcissistic
    0.86
    Activations Density 0.079%

    No Known Activations