© 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. 18727
    Prev
    Next
    INDEX
    Explanations

    the names of aircraft models

    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
    373
    +0.12
    0.6%
    333
    +0.10
    0.5%
    659
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.04
    388
    +0.10
    0.03
    115
    +0.10
    0.03
    Negative Logits
    enegger
    -0.78
    shaw
    -0.74
     humble
    -0.66
    baugh
    -0.63
     sidx
    -0.63
     cause
    -0.62
     gru
    -0.62
     Notting
    -0.62
    advertisement
    -0.62
    ebted
    -0.61
    POSITIVE LOGITS
    DF
    1.18
    TP
    1.15
    LC
    1.11
    TC
    1.11
    RP
    1.10
    OD
    1.09
    NP
    1.09
    ND
    1.06
    AC
    1.06
    DS
    1.06
    Activations Density 0.069%

    No Known Activations