© 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 24576
    9. 8-RES_FS24576-JB
    11. 7085
    Prev
    Next
    INDEX
    Explanations

    phrases related to public figures and political events

    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
    447
    +0.24
    1.1%
    481
    +0.12
    0.5%
    346
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.24
    0.08
    224
    +0.12
    0.07
    401
    +0.10
    0.07
    Negative Logits
     unlike
    -0.67
    =-=-=-=-
    -0.67
     beforehand
    -0.62
     anyways
    -0.59
     Others
    -0.58
     tho
    -0.58
    ;;;;;;;;;;;;
    -0.57
     cannabin
    -0.56
     pleasing
    -0.56
     Shutterstock
    -0.55
    POSITIVE LOGITS
     began
    1.09
     became
    0.98
     reverted
    0.96
     went
    0.95
     finally
    0.95
     embarked
    0.94
     wrote
    0.94
     abruptly
    0.94
     awoke
    0.90
     flew
    0.89
    Activations Density 0.624%

    No Known Activations