© 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. 30124
    Prev
    Next
    INDEX
    Explanations

    the word "this" and its contextual repetition in the 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
    402
    +0.12
    0.7%
    199
    +0.11
    0.6%
    478
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    199
    +0.12
    0.04
    402
    +0.11
    0.04
    187
    +0.10
    0.03
    Negative Logits
    )];
    -1.74
    )):
    -1.64
     Lung
    -1.48
    ]];
    -1.46
     Cron
    -1.37
    itin
    -1.34
    frame
    -1.32
     Lions
    -1.31
     Citizen
    -1.29
    )].
    -1.27
    POSITIVE LOGITS
    aliana
    2.00
    omer
    1.86
     often
    1.60
     blog
    1.57
    endor
    1.55
    sell
    1.55
     way
    1.48
    omers
    1.45
     supposedly
    1.45
     book
    1.40
    Activations Density 0.205%

    No Known Activations