© 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 EvalsExportsinterp-engineNEWAPI 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. 22800
    Prev
    Next
    INDEX
    Explanations

    keywords related to economic metrics and efficiencies

    oai_token-act-pair · gpt-4o-miniTriggered 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
    495
    +0.10
    0.5%
    51
    +0.10
    0.5%
    668
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.10
    0.06
    724
    +0.10
    0.06
    288
    +0.10
    0.06
    Negative Logits
    interstitial
    -0.75
    omorphic
    -0.74
     consolation
    -0.63
    oros
    -0.62
     fault
    -0.61
    bern
    -0.61
     Griffith
    -0.61
    pired
    -0.59
     Mat
    -0.59
    recated
    -0.58
    POSITIVE LOGITS
     considerably
    1.02
     exponentially
    0.99
     dramatically
    0.97
     tremendously
    0.91
     significantly
    0.90
    ahime
    0.88
     substantially
    0.87
     drastically
    0.84
     enormously
    0.83
     accordingly
    0.78
    Activations Density 0.259%

    No Known Activations