© 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 12288
    9. 8-RES_FS12288-JB
    11. 10688
    Prev
    Next
    INDEX
    Explanations

    phrases related to consistency and adherence to rules and principles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    481
    +0.12
    0.6%
    702
    +0.11
    0.5%
    26
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.05
    362
    +0.11
    0.05
    589
    +0.09
    0.03
    Negative Logits
    gins
    -0.75
    zon
    -0.73
    enaries
    -0.69
     downed
    -0.69
    lost
    -0.68
    flush
    -0.67
    enary
    -0.66
    eware
    -0.66
    NetMessage
    -0.66
    ahs
    -0.64
    POSITIVE LOGITS
     expectations
    1.02
     tradition
    0.99
     precon
    0.95
     ideals
    0.91
     beliefs
    0.88
     stereotypes
    0.87
     sensibilities
    0.86
    ¥µ
    0.84
     sentiments
    0.84
     tenets
    0.83
    Activations Density 0.249%

    No Known Activations