© 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. 9814
    Prev
    Next
    INDEX
    Explanations

    academic achievements and accolades related to scholarly activities

    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
    480
    +0.17
    0.8%
    226
    +0.09
    0.4%
    361
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.17
    0.04
    620
    +0.09
    0.01
    226
    +0.09
    0.05
    Negative Logits
    nexpected
    -0.60
    halla
    -0.56
    ixir
    -0.54
    ÙĴ
    -0.51
     ref
    -0.50
     blo
    -0.50
     frust
    -0.50
    aph
    -0.50
     âĢº
    -0.49
     POLITICO
    -0.49
    POSITIVE LOGITS
     respectively
    1.62
    collect
    0.77
     sqor
    0.75
     thereto
    0.69
    )).
    0.67
    *.
    0.64
    etheless
    0.64
     etc
    0.62
     Tradable
    0.62
     Amen
    0.61
    Activations Density 1.450%

    No Known Activations