© 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. 25154
    Prev
    Next
    INDEX
    Explanations

    the phrase "In 10"

    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
    +0.21
    1.2%
    478
    +0.19
    1.1%
    243
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.21
    0.08
    209
    +0.19
    0.06
    120
    +0.15
    0.07
    Negative Logits
    ingly
    -1.75
    ours
    -1.63
    ious
    -1.53
    entially
    -1.53
    iously
    -1.53
     Warning
    -1.51
    ament
    -1.48
    eless
    -1.46
    irs
    -1.44
    edly
    -1.44
    POSITIVE LOGITS
    ¿
    2.45
     order
    2.37
    «
    2.27
     addition
    2.25
     conjunction
    2.19
    frastructure
    2.19
    fected
    2.15
    ¿½
    2.10
     lieu
    2.03
    ¬
    2.00
    Activations Density 1.361%

    No Known Activations