© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 25653
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    160
    +0.13
    0.7%
    311
    +0.10
    0.6%
    501
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.13
    0.00
    1
    -0.10
    0.00
    2
    -0.10
    0.00
    Negative Logits
    Ģ
    -1.76
    ¬
    -1.74
    idas
    -1.68
    izumab
    -1.58
    uid
    -1.54
    album
    -1.53
    IJ
    -1.52
    jon
    -1.51
    lando
    -1.49
    ans
    -1.46
    POSITIVE LOGITS
     particular
    1.70
     desired
    1.60
     couple
    1.52
     proffered
    1.51
     convenience
    1.50
     relatively
    1.49
     either
    1.48
     wed
    1.47
     fairly
    1.45
    elia
    1.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.