© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25651
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases or words indicating a relationship or quantity

    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
    248
    +0.13
    0.7%
    417
    +0.12
    0.7%
    363
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.13
    0.03
    310
    +0.12
    0.02
    362
    +0.12
    0.02
    Negative Logits
    ť
    -1.60
    ös
    -1.54
     operator
    -1.44
    Č
    -1.42
    uder
    -1.39
     tastes
    -1.39
    her
    -1.38
     denotes
    -1.36
     notation
    -1.34
     sentence
    -1.34
    POSITIVE LOGITS
    Īĺ
    3.63
    Ļª
    3.44
    ľĵ
    3.16
    §
    3.13
    »¿
    3.02
    ĸ
    3.01
    ĵ
    3.00
    ĨĴ
    2.97
    č↵
    2.95
    2.95
    Activations Density 0.400%

    No Known Activations