© 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 1536
    9. 8-RES_FS1536-JB
    11. 1074
    Prev
    Next
    INDEX
    Explanations

    dates or time-related phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    218
    +0.10
    0.5%
    408
    +0.10
    0.4%
    84
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.10
    0.06
    147
    +0.10
    0.05
    54
    +0.09
    0.06
    Negative Logits
    pta
    -0.76
    BILITIES
    -0.72
    abus
    -0.69
    amina
    -0.69
    anie
    -0.68
    aves
    -0.65
    vantage
    -0.65
    bear
    -0.64
    obic
    -0.63
    immer
    -0.62
    POSITIVE LOGITS
    rely
    1.37
     inception
    1.13
     1945
    0.91
     1999
    0.91
     1979
    0.91
     1998
    0.90
     2006
    0.90
     2009
    0.90
     2005
    0.89
     1995
    0.88
    Activations Density 0.848%

    No Known Activations