© 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. 5658
    Prev
    Next
    INDEX
    Explanations

    comparative words or phrases indicating a higher degree of a particular quality or characteristic

    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
    389
    +0.10
    0.5%
    762
    +0.09
    0.4%
    553
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.10
    0.03
    13
    +0.09
    0.02
    726
    +0.09
    0.02
    Negative Logits
    gio
    -0.98
    ocene
    -0.80
    only
    -0.75
    meet
    -0.74
    heid
    -0.69
    ences
    -0.67
    pei
    -0.66
    uese
    -0.65
    istrates
    -0.65
    hend
    -0.65
    POSITIVE LOGITS
     stringent
    0.91
     impressive
    0.87
     ambitious
    0.86
     potent
    0.86
     challeng
    0.85
     exciting
    0.81
     disturbing
    0.79
     shocking
    0.78
     precarious
    0.78
     frightening
    0.78
    Activations Density 0.055%

    No Known Activations