© 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. 18566
    Prev
    Next
    INDEX
    Explanations

    negative situations or challenges

    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
    480
    +0.13
    0.6%
    636
    +0.10
    0.5%
    205
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.09
    616
    +0.10
    0.05
    160
    +0.10
    0.07
    Negative Logits
    ertodd
    -0.67
    bnb
    -0.67
    ĸļ
    -0.62
    atoon
    -0.62
    quickShipAvailable
    -0.62
    £ı
    -0.61
    cipled
    -0.61
    parser
    -0.59
     Newsp
    -0.58
    Newsletter
    -0.57
    POSITIVE LOGITS
     agenda
    0.86
     burden
    0.85
     workforce
    0.84
     ecosystem
    0.84
     fortunes
    0.83
     gap
    0.82
     structure
    0.82
     barrier
    0.82
     landscape
    0.81
     scourge
    0.81
    Activations Density 0.604%

    No Known Activations