© 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. 30921
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    307
    +0.14
    0.8%
    438
    +0.12
    0.7%
    189
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.14
    0.11
    204
    +0.12
    0.09
    382
    +0.10
    0.09
    Negative Logits
    ëĭĪëĭ¤
    -1.61
    ode
    -1.59
    ’
    -1.59
    ems
    -1.49
    odes
    -1.44
    UNC
    -1.44
    ovo
    -1.41
    ships
    -1.40
    Living
    -1.38
    ’,
    -1.38
    POSITIVE LOGITS
    pez
    1.85
    aman
    1.55
    être
    1.44
    hind
    1.44
    endar
    1.43
    anese
    1.42
    blockList
    1.40
    jar
    1.39
    rail
    1.36
    bourg
    1.36
    Activations Density 0.138%

    No Known Activations

    This feature has no known activations.