© 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. 0-MLP-SM
    6. 26809
    Prev
    Next
    INDEX
    Explanations

    references to clinical research and studies

    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
    119
    +0.12
    0.7%
    510
    +0.12
    0.7%
    380
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.12
    0.01
    510
    +0.12
    0.01
    380
    +0.11
    0.01
    Negative Logits
     ')
    -1.89
     BGCOLOR
    -1.72
     '')
    -1.64
    idegger
    -1.59
    ))$.
    -1.57
     MERCHANTABILITY
    -1.56
    '])
    -1.55
    ');
    -1.54
    ))$,
    -1.53
    '))
    -1.52
    POSITIVE LOGITS
    ļ
    2.63
    ŀ
    2.27
    ¾
    2.17
    fecture
    2.15
    ¢
    2.09
    ¡
    2.05
    »¿
    2.00
    º
    1.99
    £
    1.95
    ij
    1.94
    Activations Density 0.023%

    No Known Activations