© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1464
    Prev
    Next
    INDEX
    Explanations

    time-related phrases indicating the present or ongoing nature of certain situations

    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
    108
    +0.20
    0.9%
    663
    +0.11
    0.5%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.20
    0.05
    663
    +0.11
    0.03
    468
    +0.10
    0.03
    Negative Logits
     Consent
    -0.75
     sudden
    -0.64
    oops
    -0.61
     haste
    -0.60
    hens
    -0.57
     Intro
    -0.56
    kin
    -0.56
     Means
    -0.56
    Exit
    -0.55
    Fix
    -0.55
    POSITIVE LOGITS
     haunt
    0.87
     descendants
    0.83
     proudly
    0.81
     haunted
    0.75
     reverber
    0.74
    adays
    0.74
     enshr
    0.73
     extant
    0.72
     regretted
    0.72
     etched
    0.72
    Activations Density 0.210%

    No Known Activations