© 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. 9081
    Prev
    Next
    INDEX
    Explanations

    phrases indicating summarization or conclusion

    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
    679
    +0.10
    0.5%
    368
    +0.09
    0.4%
    236
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.10
    0.02
    702
    +0.09
    0.02
    236
    +0.08
    0.02
    Negative Logits
     certify
    -0.65
    eties
    -0.63
     tracker
    -0.60
     Tracker
    -0.59
    cgi
    -0.57
    den
    -0.56
    iae
    -0.56
    adders
    -0.54
    osponsors
    -0.54
     contam
    -0.54
    POSITIVE LOGITS
     succinct
    1.10
     summed
    1.00
     sentiments
    0.86
     summarized
    0.84
     concise
    0.82
     neatly
    0.78
     gist
    0.78
     nutshell
    0.77
     summar
    0.77
     sentiment
    0.73
    Activations Density 0.069%

    No Known Activations