© 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. 18492
    Prev
    Next
    INDEX
    Explanations

    information related to historical events

    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
    447
    +0.20
    0.9%
    702
    +0.11
    0.5%
    18
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.20
    0.04
    241
    +0.11
    0.05
    18
    +0.11
    0.05
    Negative Logits
    ttle
    -0.66
    ggle
    -0.65
    dule
    -0.64
    Ö¼
    -0.60
    ²¾
    -0.60
    ecause
    -0.59
    tons
    -0.59
    mut
    -0.58
    inese
    -0.57
     desserts
    -0.57
    POSITIVE LOGITS
    .;
    0.84
    Reviewed
    0.81
     Retrieved
    0.70
     Dear
    0.70
    ;;;;;;;;;;;;
    0.65
     Wikimedia
    0.64
    ometown
    0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.63
     Correspond
    0.63
     Edition
    0.62
    Activations Density 0.367%

    No Known Activations