© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 25644
    Prev
    Next
    INDEX
    Explanations

    terminology related to fields and categories in various contexts

    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
    474
    +0.13
    0.8%
    155
    +0.12
    0.6%
    504
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.13
    0.01
    120
    +0.12
    0.01
    504
    +0.11
    0.00
    Negative Logits
    »¿
    -3.48
    ĻĤ
    -3.44
    ĵ
    -2.71
    Ģ
    -2.67
    Ļª
    -2.62
    ŀ
    -2.55
    ĩ
    -2.53
    Į
    -2.50
    ģ
    -2.47
    Ł
    -2.45
    POSITIVE LOGITS
    hing
    1.54
    cing
    1.50
    rent
    1.47
    ableness
    1.47
     rather
    1.39
     equivalently
    1.39
    ="{
    1.34
    ="{{
    1.32
    uously
    1.31
     Value
    1.29
    Activations Density 0.044%

    No Known Activations