© 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 EvalsExportsinterp-engineNEWAPI 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. 20995
    Prev
    Next
    INDEX
    Explanations

    common phrases and terms used in politics and current 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
    481
    +0.20
    0.9%
    745
    +0.09
    0.4%
    620
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.08
    225
    +0.09
    0.06
    762
    +0.09
    0.07
    Negative Logits
    ITNESS
    -0.73
    ificantly
    -0.73
    aughtered
    -0.69
    ificant
    -0.62
     %%
    -0.61
    inally
    -0.60
     Investig
    -0.58
    untled
    -0.58
     )]
    -0.57
    PLA
    -0.57
    POSITIVE LOGITS
     altogether
    0.98
     lest
    0.81
     inhib
    0.77
     anymore
    0.76
     into
    0.73
    NetMessage
    0.73
     confines
    0.72
     clich
    0.72
     preferring
    0.68
     notions
    0.67
    Activations Density 0.601%

    No Known Activations