© 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. 30677
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of specific names and terms, particularly related to notable individuals and works

    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
    16
    +0.12
    0.6%
    485
    +0.11
    0.6%
    323
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.03
    16
    +0.11
    0.02
    429
    +0.10
    0.02
    Negative Logits
    adier
    -1.50
     advance
    -1.46
    ASE
    -1.41
     objective
    -1.33
    zol
    -1.30
     alert
    -1.30
     error
    -1.29
     contradiction
    -1.27
    \'
    -1.27
     age
    -1.27
    POSITIVE LOGITS
    3.36
    3.36
    ↵
    3.36
    ↵
    3.36
     ↵
    3.36
    3.36
    č↵
    3.36
    ↵↵
    3.36
    ↵
    3.36
    3.36
    Activations Density 0.266%

    No Known Activations