© 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. 0-MLP-SM
    11. 28181
    Prev
    Next
    INDEX
    Explanations

    the term "QU" indicating a requirement, particularly in programming or technical specifications

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    243
    +0.15
    0.8%
    369
    +0.13
    0.7%
    203
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.15
    0.02
    223
    +0.13
    0.02
    314
    +0.12
    0.01
    Negative Logits
     answered
    -2.01
     replied
    -1.66
    -1.63
    -1.63
    ↵↵
    -1.63
    ↵↵
    -1.63
    <|outofrange|>
    -1.63
    Â
    -1.63
    ↵↵
    -1.63
    -1.63
    POSITIVE LOGITS
    iary
    1.74
    iu
    1.72
    ibase
    1.72
    ete
    1.70
    iere
    1.69
     beds
    1.69
    eries
    1.62
    etto
    1.61
    itol
    1.55
    erals
    1.55
    Activations Density 0.010%

    No Known Activations