© 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. 2-MLP-SM
    11. 22328
    Prev
    Next
    INDEX
    Explanations

    actions and changes in state or conditions

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    369
    +0.14
    0.8%
    213
    +0.11
    0.6%
    98
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.14
    0.09
    295
    +0.11
    0.09
    173
    +0.11
    0.06
    Negative Logits
    fected
    -1.66
    akov
    -1.61
    ameter
    -1.47
     hereto
    -1.47
    istically
    -1.45
     evenly
    -1.45
     desir
    -1.44
    !}
    -1.43
    \]]{}
    -1.42
    )].
    -1.41
    POSITIVE LOGITS
    bie
    1.70
    ius
    1.69
    ³
    1.53
    ¹
    1.52
    ivism
    1.48
    writers
    1.43
    ollah
    1.42
    ientes
    1.42
    ±
    1.40
     colleagues
    1.36
    Activations Density 0.845%

    No Known Activations