© 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. 26851
    Prev
    Next
    INDEX
    Explanations

    occurrences of file license information

    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
    23
    +0.26
    1.5%
    478
    +0.16
    0.9%
    403
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.26
    0.04
    12
    +0.16
    0.04
    306
    +0.14
    0.03
    Negative Logits
    ·¸
    -2.31
    ·
    -1.86
    ista
    -1.79
     sponsor
    -1.77
    äsident
    -1.73
    µ
    -1.72
    ¼
    -1.72
    iven
    -1.71
    ¿½
    -1.68
    ishers
    -1.68
    POSITIVE LOGITS
     finding
    1.88
     ye
    1.68
      ↵
    1.63
     hence
    1.47
    -)
    1.45
     existence
    1.42
     seeing
    1.40
     my
    1.39
    und
    1.38
    anson
    1.38
    Activations Density 1.687%

    No Known Activations