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

    Neuronpedia

    Jacobian LensNEW
    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. 7870
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving a specific goal through collaboration and support

    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
    481
    +0.36
    1.7%
    154
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.36
    0.05
    481
    +0.11
    0.08
    762
    +0.10
    0.08
    Negative Logits
    pired
    -0.56
    Ku
    -0.56
    \":
    -0.55
    ãĤ«
    -0.53
    stood
    -0.50
    BuyableInstoreAndOnline
    -0.49
    SPONSORED
    -0.48
     Chancellor
    -0.48
     Ply
    -0.47
    ench
    -0.47
    POSITIVE LOGITS
     anytime
    1.07
     yourself
    0.98
     WITHOUT
    0.94
     someday
    0.92
     myself
    0.91
     without
    0.89
     manually
    0.88
     whenever
    0.87
     depending
    0.87
     ourselves
    0.87
    Activations Density 0.786%

    No Known Activations