© 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. 18428
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes related to content placement, such as container and thumbnails, within a web document

    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
    +0.52
    2.8%
    314
    +0.13
    0.7%
    266
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.52
    0.01
    266
    +0.13
    0.07
    314
    +0.11
    -0.01
    Negative Logits
    uddin
    -0.65
    iland
    -0.64
    reflect
    -0.51
     Samoa
    -0.51
    yip
    -0.50
     Ukrain
    -0.50
    achu
    -0.48
    ivating
    -0.48
    aterasu
    -0.48
    enhagen
    -0.48
    POSITIVE LOGITS
    earances
    0.58
    odder
    0.54
    endment
    0.54
    letters
    0.54
    Dialogue
    0.53
     Entry
    0.53
    ept
    0.53
     fixme
    0.53
    ħĭ
    0.51
     LLP
    0.51
    Activations Density 0.715%

    No Known Activations