© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26887
    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
    325
    +0.16
    0.9%
    457
    +0.13
    0.7%
    310
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.16
    0.38
    151
    +0.13
    0.31
    434
    +0.12
    0.30
    Negative Logits
     checkbox
    -1.59
     preceded
    -1.54
    ---|---
    -1.53
    icity
    -1.52
    ocation
    -1.51
    nbsp
    -1.47
     duration
    -1.45
    ly
    -1.43
     period
    -1.43
     premium
    -1.43
    POSITIVE LOGITS
    reon
    1.74
    !”
    1.61
    ellants
    1.53
    uu
    1.50
    ric
    1.50
    efore
    1.49
     appeal
    1.46
    urious
    1.45
    initis
    1.43
     apologize
    1.40
    Activations Density 1.639%

    No Known Activations

    This feature has no known activations.