© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3348
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethics and societal issues, including discussions around morality, government rights, and societal responsibilities

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    510
    +0.11
    0.5%
    53
    +0.10
    0.5%
    101
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    510
    +0.11
    0.04
    53
    +0.10
    0.04
    647
    +0.10
    0.04
    Negative Logits
    OUS
    -0.60
    SIGN
    -0.59
    ASED
    -0.57
    ALLY
    -0.56
    KN
    -0.55
    erial
    -0.54
     Timbers
    -0.54
    ORY
    -0.54
     Finger
    -0.54
    KNOWN
    -0.54
    POSITIVE LOGITS
    bestos
    1.15
     opposed
    1.13
     evidenced
    1.10
    pires
    0.99
    pects
    0.94
    cription
    0.92
    ylum
    0.92
    printf
    0.90
    pired
    0.90
    piration
    0.89
    Activations Density 0.091%

    No Known Activations