© 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. 18749
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions and narrative elements related to various storylines, particularly focusing on interpersonal relationships and character dynamics

    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
    640
    +0.29
    1.4%
    87
    +0.14
    0.7%
    64
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.29
    0.14
    64
    +0.14
    -0.03
    94
    +0.13
    0.10
    Negative Logits
     footing
    -0.67
     engagement
    -0.62
     communications
    -0.62
     manoeuv
    -0.61
     Communications
    -0.60
     Trog
    -0.59
     Arbit
    -0.59
    lling
    -0.58
     ideal
    -0.58
     outright
    -0.57
    POSITIVE LOGITS
    ³³³³³³³³
    1.18
    ³³³³³³³³³³³³³³³³
    1.14
    ³³³³
    1.14
    advertisement
    1.11
    Anyway
    1.10
    ³³³
    1.07
    Advertisement
    1.00
    Article
    0.93
    posted
    0.89
    Thankfully
    0.88
    Activations Density 0.329%

    No Known Activations