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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 25978
    Prev
    Next
    INDEX
    Explanations

    instances of "pairs" and "triplets", particularly in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.15
    0.9%
    139
    +0.13
    0.7%
    466
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    487
    +0.15
    0.01
    139
    +0.13
    0.01
    466
    +0.12
    0.01
    Negative Logits
    woke
    -1.91
    µ
    -1.67
    rapy
    -1.63
    ©
    -1.59
     assumption
    -1.58
     sudden
    -1.56
     MERCHANTABILITY
    -1.54
    YLE
    -1.52
    orems
    -1.49
     stripes
    -1.45
    POSITIVE LOGITS
    cript
    2.03
    het
    1.86
    manship
    1.84
    hoe
    1.83
    iative
    1.81
    amente
    1.78
    wise
    1.76
    uar
    1.74
    cores
    1.72
    nikov
    1.69
    Activations Density 0.005%

    No Known Activations