© 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. 26763
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or references to quality or superiority

    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
    400
    +0.12
    0.7%
    456
    +0.11
    0.6%
    182
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.12
    0.39
    98
    +0.11
    0.15
    228
    +0.10
    0.26
    Negative Logits
    uary
    -1.57
     tomography
    -1.56
    rophe
    -1.56
    ircon
    -1.55
    rz
    -1.53
    rome
    -1.50
    uchi
    -1.49
    ata
    -1.48
    atrix
    -1.47
    ors
    -1.44
    POSITIVE LOGITS
    dependencies
    1.45
    ");
    1.43
    .”
    1.42
    play
    1.41
     miss
    1.40
    ”
    1.36
    iest
    1.36
    publish
    1.35
     Lomb
    1.34
    ”).
    1.33
    Activations Density 2.944%

    No Known Activations