© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23107
    Prev
    Next
    INDEX
    Explanations

    plural forms and suffix variations of nouns

    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
    23
    +0.17
    1.0%
    303
    +0.12
    0.7%
    9
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.05
    18
    +0.12
    0.04
    133
    +0.12
    0.06
    Negative Logits
    $}
    -1.55
    $).
    -1.44
    ourier
    -1.42
    duct
    -1.41
    hematic
    -1.41
    taient
    -1.40
    heets
    -1.40
    phon
    -1.36
    1471
    -1.36
    80211
    -1.36
    POSITIVE LOGITS
     ger
    1.51
    illary
    1.50
    gaard
    1.50
    ª
    1.48
    ¹
    1.48
    anian
    1.40
    erl
    1.38
     Ger
    1.35
     if
    1.33
     reviewed
    1.32
    Activations Density 0.557%

    No Known Activations