© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9396
    Prev
    Next
    INDEX
    Explanations

    dialogue interactions, including expressions of conflict, love, and communication

    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
    698
    +0.10
    0.5%
    446
    +0.09
    0.4%
    393
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.10
    0.08
    43
    +0.09
    0.07
    297
    +0.09
    0.07
    Negative Logits
    itational
    -0.79
    ourse
    -0.72
    ourses
    -0.71
    iffe
    -0.69
    irie
    -0.69
    ursive
    -0.68
    reated
    -0.67
    Forge
    -0.67
    requently
    -0.66
    esa
    -0.66
    POSITIVE LOGITS
     huh
    1.70
     eh
    1.53
     haha
    1.34
     sir
    1.28
     yeah
    1.07
     anyways
    0.97
     lol
    0.96
     anyway
    0.94
     alright
    0.91
     tho
    0.91
    Activations Density 0.458%

    No Known Activations