© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 3072
    9. 8-RES_FS3072-JB
    11. 250
    Prev
    Next
    INDEX
    Explanations

    phrases related to political commentary

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    435
    +0.10
    0.5%
    300
    +0.10
    0.4%
    86
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.10
    0.13
    105
    +0.10
    0.08
    435
    +0.09
    0.06
    Negative Logits
    ties
    -0.64
    iannopoulos
    -0.63
    ilk
    -0.62
    Ö¼
    -0.59
    RANT
    -0.59
    host
    -0.58
     unlucky
    -0.58
     Hilbert
    -0.57
    LAN
    -0.57
     unexpectedly
    -0.56
    POSITIVE LOGITS
     urgently
    1.31
     rethink
    1.31
     reconsider
    1.24
     ASAP
    1.05
    cknow
    1.02
     recons
    1.00
     humility
    0.97
     reinvest
    0.94
     compassion
    0.93
     wiser
    0.92
    Activations Density 2.507%

    No Known Activations