© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25035
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe the manner of actions or states

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    242
    +0.15
    0.9%
    438
    +0.12
    0.7%
    460
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.15
    0.02
    460
    +0.12
    0.01
    468
    +0.12
    0.01
    Negative Logits
    Ĥ¬
    -2.49
    Ģ
    -2.39
    ®
    -2.36
    ²
    -2.31
    ·¸
    -2.31
    ¨
    -2.29
    Ĭ
    -2.29
    ħ
    -2.24
    »¿
    -2.22
    ¯
    -2.21
    POSITIVE LOGITS
    caster
    1.54
    fecture
    1.46
    vereign
    1.37
     Janeiro
    1.37
    dit
    1.36
    dehyde
    1.36
    ière
    1.34
     assault
    1.34
    ium
    1.32
     Election
    1.31
    Activations Density 0.032%

    No Known Activations