© 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. 0-MLP-SM
    11. 29509
    Prev
    Next
    INDEX
    Explanations

    words related to growth or cultivation

    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
    331
    +0.12
    0.7%
    117
    +0.11
    0.6%
    189
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.01
    331
    +0.11
    0.01
    432
    +0.10
    0.01
    Negative Logits
    Ļª
    -2.61
    »¿
    -1.92
    ĨĴ
    -1.86
     bother
    -1.80
      ↵
    -1.73
    zzle
    -1.70
    psin
    -1.61
     mere
    -1.59
     largest
    -1.56
    rely
    -1.53
    POSITIVE LOGITS
    ettes
    2.02
    arie
    1.96
    endas
    1.87
    ató
    1.87
    ators
    1.70
    #:
    1.70
    works
    1.66
    uary
    1.60
    heets
    1.59
    naire
    1.56
    Activations Density 0.020%

    No Known Activations