© 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. 30680
    Prev
    Next
    INDEX
    Explanations

    repeated conjunctions in text

    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
    499
    +0.13
    0.7%
    357
    +0.11
    0.6%
    248
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.13
    0.45
    209
    +0.11
    0.28
    402
    +0.11
    0.25
    Negative Logits
    olite
    -1.79
     close
    -1.76
    rous
    -1.68
     closer
    -1.62
     bacteria
    -1.59
    ashi
    -1.58
     roughly
    -1.53
     commens
    -1.51
    rians
    -1.50
    orian
    -1.50
    POSITIVE LOGITS
    ±
    2.75
    ¾
    2.71
    ¸
    2.68
    ²
    2.67
    ī
    2.59
    Ĭ
    2.59
    «
    2.49
    ¤
    2.48
    »¿
    2.46
    ¥
    2.44
    Activations Density 1.859%

    No Known Activations