© 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. 31199
    Prev
    Next
    INDEX
    Explanations

    the repeated occurrence of the token "ella"

    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
    376
    +0.16
    0.9%
    269
    +0.13
    0.8%
    503
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.16
    0.01
    44
    +0.13
    0.01
    419
    +0.13
    0.01
    Negative Logits
    ¿½
    -1.84
    soever
    -1.68
    ?'
    -1.66
    '));
    -1.60
     hither
    -1.60
    rap
    -1.59
     thou
    -1.59
    '?"
    -1.57
    ANS
    -1.53
     mistaken
    -1.52
    POSITIVE LOGITS
     circuit
    1.79
    ruptcy
    1.71
     defenses
    1.66
    enstein
    1.65
    heim
    1.61
    circuit
    1.61
     Snyder
    1.60
    idity
    1.59
    film
    1.59
    lists
    1.58
    Activations Density 0.017%

    No Known Activations