© 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. 29719
    Prev
    Next
    INDEX
    Explanations

    repeated patterns or instances of the same exact phrase or term

    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
    241
    +0.13
    0.7%
    16
    +0.12
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.13
    0.02
    105
    +0.12
    0.02
    16
    +0.12
    0.02
    Negative Logits
     moderation
    -1.85
    Īĺ
    -1.73
     too
    -1.73
    ĥ½
    -1.69
     forgotten
    -1.68
    ľ
    -1.66
    ¿½
    -1.64
     fair
    -1.63
    §
    -1.63
    ¼
    -1.57
    POSITIVE LOGITS
    cript
    2.05
    loop
    1.80
    CRIPTION
    1.79
    creen
    1.70
    olver
    1.66
    enger
    1.62
    borough
    1.59
    esan
    1.57
    cores
    1.54
    holes
    1.54
    Activations Density 0.112%

    No Known Activations