© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10429
    Prev
    Next
    INDEX
    Explanations

    activity or actions related to preparation or planning

    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
    710
    +0.14
    0.6%
    0
    +0.12
    0.5%
    649
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.14
    0.03
    0
    +0.12
    0.02
    433
    +0.12
    0.02
    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.83
    loo
    -0.75
    è¦ļéĨĴ
    -0.73
    ãĤ¼ãĤ¦ãĤ¹
    -0.72
     GOODMAN
    -0.71
    IBLE
    -0.71
    oice
    -0.69
    ourcing
    -0.67
    BuyableInstoreAndOnline
    -0.63
     Weir
    -0.62
    POSITIVE LOGITS
    cision
    1.26
    pared
    1.22
    cious
    1.21
    cise
    1.20
    requisites
    1.18
    hens
    1.13
    requisite
    1.12
    ferred
    1.09
    empt
    1.08
    historic
    1.05
    Activations Density 0.019%

    No Known Activations