© 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. 25561
    Prev
    Next
    INDEX
    Explanations

    URL query parameters

    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
    332
    +0.14
    0.8%
    249
    +0.12
    0.7%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.14
    0.03
    318
    +0.12
    0.01
    18
    +0.11
    0.01
    Negative Logits
     exception
    -1.60
     swallowing
    -1.54
     offensive
    -1.46
    mouth
    -1.45
    erville
    -1.37
     signatures
    -1.35
     frustrated
    -1.34
    issions
    -1.32
    rophe
    -1.31
     ever
    -1.30
    POSITIVE LOGITS
    Ļª
    2.33
    »
    2.32
    ĭ
    2.17
    ¿
    2.15
    ļ
    2.13
    ľ
    2.12
    ĩ
    2.11
    «
    2.08
    ¾
    2.07
    ¶
    1.96
    Activations Density 0.172%

    No Known Activations