© 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. 8896
    Prev
    Next
    INDEX
    Explanations

    adjectives relating to the magnitude or extent of something

    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
    102
    +0.11
    0.5%
    76
    +0.10
    0.5%
    151
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.11
    0.06
    190
    +0.10
    0.05
    106
    +0.10
    0.05
    Negative Logits
    eday
    -0.91
    ĺħ
    -0.80
     Tags
    -0.72
    ydia
    -0.67
     Korea
    -0.66
     Females
    -0.66
    odore
    -0.66
     Shutterstock
    -0.65
    OGR
    -0.63
     Landing
    -0.63
    POSITIVE LOGITS
     contradictory
    0.90
     volatile
    0.89
     innocuous
    0.88
     chaotic
    0.88
     lethal
    0.88
     unorthodox
    0.87
     conflicting
    0.84
     turbulent
    0.83
     tumultuous
    0.83
     divisive
    0.83
    Activations Density 0.143%

    No Known Activations