© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23999
    Prev
    Next
    INDEX
    Explanations

    references to endocannabinoids and their related receptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.25
    1.4%
    23
    +0.13
    0.7%
    181
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.25
    0.02
    140
    +0.13
    0.03
    335
    +0.12
    0.03
    Negative Logits
    į
    -2.64
    Ľ
    -1.89
    :`
    -1.81
    '."
    -1.78
    »
    -1.78
    .'"
    -1.78
    ».
    -1.75
    ème
    -1.72
    £
    -1.69
    ."[
    -1.68
    POSITIVE LOGITS
     prices
    1.59
     temperatures
    1.43
     Tas
    1.43
     Cornwall
    1.41
     benchmarks
    1.41
     anyone
    1.39
     leagues
    1.37
     Lab
    1.36
     Ltd
    1.34
     USDA
    1.34
    Activations Density 0.189%

    No Known Activations