© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 16071
    Prev
    Next
    INDEX
    Explanations

    sections of text that involve recounting events or conversations

    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
    373
    +0.16
    0.8%
    450
    +0.09
    0.4%
    137
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.16
    0.04
    582
    +0.09
    0.04
    450
    +0.09
    0.04
    Negative Logits
    industrial
    -0.70
    zbollah
    -0.65
     GD
    -0.64
     OECD
    -0.63
     EVs
    -0.63
     Historically
    -0.59
    adium
    -0.57
     historically
    -0.57
     Critics
    -0.57
     Supporters
    -0.57
    POSITIVE LOGITS
    upon
    1.03
    Soon
    0.96
    Eventually
    0.94
    Later
    0.91
     prest
    0.90
     Soon
    0.84
     ensued
    0.83
     thereafter
    0.83
    nown
    0.81
     soon
    0.80
    Activations Density 0.627%

    No Known Activations