© 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. 22772
    Prev
    Next
    INDEX
    Explanations

    references to energy production and consumption concepts

    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
    594
    +0.13
    0.6%
    570
    +0.12
    0.6%
    664
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.13
    0.02
    594
    +0.12
    0.04
    664
    +0.10
    0.04
    Negative Logits
     Mock
    -0.90
     Breach
    -0.76
     invites
    -0.75
    names
    -0.75
     plagiar
    -0.74
     invite
    -0.73
    review
    -0.72
     Judicial
    -0.71
     notoriety
    -0.71
     resemblance
    -0.70
    POSITIVE LOGITS
     combustion
    1.20
     electroly
    1.15
     pumps
    1.06
     efficiently
    1.06
     electricity
    1.04
     gases
    1.02
     generators
    1.02
     recharge
    1.02
    absor
    1.00
    energy
    1.00
    Activations Density 0.508%

    No Known Activations