© 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. 0-MLP-SM
    6. 27957
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds or substances

    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
    111
    +0.15
    0.8%
    317
    +0.11
    0.6%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    161
    +0.11
    0.01
    420
    +0.11
    0.01
    Negative Logits
    ?>
    -1.49
     occasional
    -1.45
    *>(
    -1.42
     rupture
    -1.38
     sudden
    -1.37
     Lisbon
    -1.36
    ITAL
    -1.35
     const
    -1.34
     stray
    -1.34
    <!--
    -1.32
    POSITIVE LOGITS
    istor
    1.92
    bilt
    1.59
    ledge
    1.57
    gos
    1.57
    blood
    1.55
    obar
    1.53
    iliar
    1.53
    imately
    1.51
    istical
    1.51
    eto
    1.50
    Activations Density 2.951%

    No Known Activations