© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 1520
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to institutions, titles, and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    127
    +0.10
    0.5%
    278
    +0.10
    0.4%
    466
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.07
    146
    +0.10
    0.05
    31
    +0.09
    0.04
    Negative Logits
    ï¸ı
    -0.84
     Moonlight
    -0.65
    pload
    -0.65
    yss
    -0.64
    selves
    -0.63
    ï¸
    -0.61
    ansson
    -0.60
     Razer
    -0.60
     Aires
    -0.58
     generation
    -0.58
    POSITIVE LOGITS
     troopers
    0.93
     trooper
    0.91
    hyde
    0.82
    aucuses
    0.79
     Trooper
    0.76
     Insurance
    0.74
     Militia
    0.72
     legislatures
    0.67
    ciating
    0.67
     lieutenant
    0.66
    Activations Density 0.513%

    No Known Activations