© 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. 25450
    Prev
    Next
    INDEX
    Explanations

    file system commands and operations in programming 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
    459
    +0.12
    0.7%
    238
    +0.12
    0.7%
    440
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.12
    0.03
    317
    +0.12
    0.04
    56
    +0.10
    0.04
    Negative Logits
     lawmakers
    -1.59
     senators
    -1.50
     itself
    -1.50
     yourself
    -1.48
     <<
    -1.44
     **(
    -1.39
     read
    -1.38
     job
    -1.37
     oneself
    -1.36
     your
    -1.36
    POSITIVE LOGITS
    á̝
    1.86
    anton
    1.72
    à°¿
    1.67
    áŁ
    1.65
    á̬
    1.63
    à±į
    1.52
    àµį
    1.49
    ık
    1.49
    áŀ
    1.47
    á̏
    1.47
    Activations Density 0.611%

    No Known Activations