© 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 24576
    5. 8-RES_FS24576-JB
    6. 20235
    Prev
    Next
    INDEX
    Explanations

    information related to sports transfers

    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
    481
    +0.12
    0.5%
    493
    +0.12
    0.5%
    502
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.08
    86
    +0.12
    0.05
    286
    +0.11
    0.05
    Negative Logits
     nonviolent
    -0.94
    colored
    -0.89
     Navajo
    -0.86
     neighborhoods
    -0.86
     nonprofits
    -0.85
     nonpartisan
    -0.85
     ACLU
    -0.84
     statewide
    -0.84
     ++
    -0.84
     federally
    -0.82
    POSITIVE LOGITS
     rumours
    1.48
    iverpool
    1.33
     enqu
    1.31
     Fifa
    1.29
     Newcastle
    1.27
     Whilst
    1.27
     realise
    1.27
     Liverpool
    1.25
     Leicester
    1.22
     £
    1.21
    Activations Density 0.883%

    No Known Activations