© 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. 19481
    Prev
    Next
    INDEX
    Explanations

    information about published articles

    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
    +0.15
    0.7%
    335
    +0.09
    0.4%
    306
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.15
    0.03
    455
    +0.09
    0.03
    739
    +0.08
    0.02
    Negative Logits
     Maid
    -0.62
    eur
    -0.59
    Lens
    -0.58
    sed
    -0.58
    agos
    -0.57
    hower
    -0.57
    jri
    -0.55
     Mant
    -0.55
    bats
    -0.52
    bos
    -0.51
    POSITIVE LOGITS
     reprinted
    0.73
     appl
    0.73
     Detected
    0.65
     POLITICO
    0.64
     largeDownload
    0.61
     Species
    0.60
    ãĤ·ãĥ£
    0.59
     column
    0.58
    én
    0.58
     isEnabled
    0.57
    Activations Density 0.048%

    No Known Activations