© 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. 24303
    Prev
    Next
    INDEX
    Explanations

    words related to animals or their physical attributes

    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
    +0.20
    1.1%
    332
    +0.12
    0.7%
    381
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.20
    0.07
    332
    +0.12
    0.08
    162
    +0.12
    0.08
    Negative Logits
    ard
    -1.62
    Ŀ
    -1.61
    ards
    -1.55
    arer
    -1.54
    riors
    -1.51
    ariat
    -1.49
    iers
    -1.46
    ounces
    -1.45
    ÑģÑı
    -1.43
    ł
    -1.40
    POSITIVE LOGITS
     herself
    1.63
     Trade
    1.53
     owned
    1.43
     share
    1.39
    ](
    1.38
     hers
    1.38
    ushi
    1.36
    brew
    1.34
    MO
    1.30
    friendly
    1.30
    Activations Density 0.914%

    No Known Activations