© 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. 18218
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of sentences

    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
    +0.12
    0.5%
    385
    +0.10
    0.5%
    84
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    704
    +0.12
    0.02
    176
    +0.10
    0.01
    394
    +0.10
    0.01
    Negative Logits
    edi
    -0.81
    vale
    -0.77
    iera
    -0.70
     grocer
    -0.68
    vez
    -0.67
    angan
    -0.65
    lude
    -0.63
    izz
    -0.63
    edient
    -0.61
    erville
    -0.61
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.79
     Identified
    0.76
     Includes
    0.75
     [+
    0.75
     Survive
    0.75
     Prol
    0.75
     Continuous
    0.72
     Hold
    0.72
     Thou
    0.71
     Opinion
    0.68
    Activations Density 0.049%

    No Known Activations