© 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. 12453
    Prev
    Next
    INDEX
    Explanations

    words related to location and proximity

    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
    59
    +0.13
    0.6%
    189
    +0.10
    0.4%
    707
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.13
    0.03
    725
    +0.10
    0.03
    707
    +0.10
    0.03
    Negative Logits
    enez
    -0.63
    ãĥ£
    -0.63
    tec
    -0.62
     goodbye
    -0.61
    FORE
    -0.61
    rey
    -0.60
    lan
    -0.60
    ennes
    -0.59
    ense
    -0.59
    Ger
    -0.59
    POSITIVE LOGITS
     bounds
    0.87
     reach
    0.87
    ciating
    0.83
    isine
    0.83
    ¥ŀ
    0.82
    ĵĺ
    0.81
    ĨĴ
    0.80
     Reach
    0.79
    ģĸ
    0.78
     parentheses
    0.78
    Activations Density 0.026%

    No Known Activations