© 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 24576
    9. 8-RES_FS24576-JB
    11. 20160
    Prev
    Next
    INDEX
    Explanations

    instances of time-related contexts and descriptions

    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
    408
    +0.13
    0.6%
    33
    +0.09
    0.4%
    609
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.13
    0.04
    737
    +0.09
    0.03
    422
    +0.09
    0.02
    Negative Logits
    ahime
    -0.88
    utics
    -0.74
    FIG
    -0.69
     [|
    -0.68
    tnc
    -0.67
    ensions
    -0.66
    assetsadobe
    -0.65
    actionDate
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
     Lauder
    -0.63
    POSITIVE LOGITS
    soever
    0.95
     sane
    0.87
     whatsoever
    0.84
     conceivable
    0.83
     remotely
    0.79
     anymore
    0.78
     remaining
    0.77
     ever
    0.76
     EVER
    0.75
     semblance
    0.75
    Activations Density 0.118%

    No Known Activations