© 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. 13234
    Prev
    Next
    INDEX
    Explanations

    the word "step" with various numerical modifiers

    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
    13
    +0.13
    0.6%
    202
    +0.10
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    13
    +0.13
    0.03
    435
    +0.10
    0.02
    450
    +0.10
    0.02
    Negative Logits
    rums
    -0.81
    olls
    -0.78
    inately
    -0.76
    iqueness
    -0.71
    rys
    -0.70
     Sins
    -0.69
    arus
    -0.66
    ores
    -0.66
    ancies
    -0.66
     Pengu
    -0.65
    POSITIVE LOGITS
     toward
    1.12
     towards
    1.08
    step
    1.02
     steps
    1.02
    steps
    0.99
     step
    0.99
     Steps
    0.93
    hens
    0.91
     forward
    0.90
    Step
    0.85
    Activations Density 0.025%

    No Known Activations