© 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 49152
    9. 8-RES_FS49152-JB
    11. 37503
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating varying impacts on children and voters based on different circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    347
    +0.13
    0.6%
    562
    +0.10
    0.5%
    469
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.13
    0.03
    469
    +0.10
    0.02
    562
    +0.10
    0.03
    Negative Logits
     symbolism
    -0.69
     wrench
    -0.63
     resemb
    -0.59
     grievance
    -0.58
     trademarks
    -0.58
     intrigue
    -0.57
     passions
    -0.57
     grievances
    -0.56
     miracles
    -0.56
     translator
    -0.55
    POSITIVE LOGITS
    dL
    0.81
    average
    0.80
    icient
    0.79
     otherwise
    0.77
    amphetamine
    0.75
    oldown
    0.74
    abet
    0.74
    rats
    0.73
    entary
    0.72
    normal
    0.71
    Activations Density 0.118%

    No Known Activations