© 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. 8988
    Prev
    Next
    INDEX
    Explanations

    phrases related to future events or potential outcomes

    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
    88
    +0.11
    0.5%
    448
    +0.10
    0.4%
    581
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    462
    +0.11
    0.03
    55
    +0.10
    0.03
    448
    +0.08
    0.02
    Negative Logits
    oire
    -0.65
    ondo
    -0.62
    ampa
    -0.61
    toe
    -0.60
    chant
    -0.60
     Enhancement
    -0.57
    ritch
    -0.57
     inspiration
    -0.57
    lations
    -0.57
    ples
    -0.56
    POSITIVE LOGITS
     termed
    0.96
    forth
    0.86
     arguably
    0.81
     aptly
    0.74
     euphem
    0.73
    wikipedia
    0.72
    ij士
    0.72
    imir
    0.72
     amounted
    0.71
     essentially
    0.68
    Activations Density 0.115%

    No Known Activations