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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 854
    Prev
    Next
    INDEX
    Explanations

    arguments and discussions related to ethics and morality

    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
    447
    +0.16
    0.8%
    297
    +0.10
    0.5%
    43
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.16
    0.04
    632
    +0.10
    0.04
    596
    +0.10
    0.05
    Negative Logits
    alysed
    -0.89
    pec
    -0.77
    SourceFile
    -0.71
    MpServer
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    olves
    -0.62
    orable
    -0.61
    olved
    -0.60
    abled
    -0.60
    /
    -0.59
    POSITIVE LOGITS
     nobody
    0.92
     there
    0.92
     imagine
    0.91
     yeah
    0.90
     if
    0.88
     why
    0.84
     suppose
    0.84
     yes
    0.80
     it
    0.80
     although
    0.78
    Activations Density 0.217%

    No Known Activations