© 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. 26980
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "of"

    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
    420
    +0.15
    0.8%
    178
    +0.13
    0.7%
    95
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.15
    0.06
    70
    +0.13
    0.06
    404
    +0.12
    0.06
    Negative Logits
    ª
    -1.84
    azzo
    -1.81
    «
    -1.70
    ¿½
    -1.69
    ĻĤ
    -1.69
    ħ
    -1.68
    ĭ
    -1.51
    ©
    -1.50
    ¼
    -1.44
    Ħ
    -1.43
    POSITIVE LOGITS
    sed
    1.54
     Punjab
    1.40
    abel
    1.39
    amil
    1.38
    ogether
    1.34
    sell
    1.33
    roph
    1.31
     sovereign
    1.31
     Saskatchewan
    1.30
    ultan
    1.29
    Activations Density 0.537%

    No Known Activations