© 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. 24178
    Prev
    Next
    INDEX
    Explanations

    technical terms related to machinery and systems in a gaming or mechanical context

    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
    447
    +0.20
    0.9%
    326
    +0.12
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.20
    0.06
    288
    +0.12
    0.07
    289
    +0.10
    0.01
    Negative Logits
    soDeliveryDate
    -0.90
    çīĪ
    -0.89
     Weiner
    -0.81
    displayText
    -0.81
     ÂŃ
    -0.81
    çĶ°
    -0.80
     Woodward
    -0.77
     Lerner
    -0.76
     Epstein
    -0.73
    internet
    -0.73
    POSITIVE LOGITS
     turrets
    1.29
     armor
    1.28
     spawns
    1.21
     armour
    1.17
     teleport
    1.15
     respawn
    1.13
     turret
    1.13
     mech
    1.09
     grenades
    1.08
     cooldown
    1.08
    Activations Density 0.315%

    No Known Activations