© 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. 31162
    Prev
    Next
    INDEX
    Explanations

    the concept of completion or finalization in various contexts

    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
    329
    +0.13
    0.7%
    376
    +0.12
    0.7%
    444
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.13
    0.01
    46
    +0.12
    0.01
    82
    +0.11
    0.01
    Negative Logits
    Ĵ
    -2.58
    ĨĴ
    -2.37
    §
    -2.21
    ľ
    -2.18
    ģ
    -2.08
    ī
    -2.08
    ĵ
    -2.06
    ŀ
    -1.99
    Ī
    -1.98
    Ł
    -1.95
    POSITIVE LOGITS
     stance
    1.90
     touches
    1.75
     angle
    1.66
    notes
    1.56
     forth
    1.55
     pains
    1.52
     posture
    1.52
     point
    1.49
    uary
    1.49
     teeth
    1.49
    Activations Density 0.025%

    No Known Activations