© 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. 30635
    Prev
    Next
    INDEX
    Explanations

    references to plotting and graphing in Python programming

    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
    412
    +0.12
    0.7%
    71
    +0.11
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.12
    0.01
    452
    +0.11
    0.01
    71
    +0.11
    0.01
    Negative Logits
    unnumbered
    -2.10
    rogens
    -1.97
      ↵
    -1.80
    ...?"
    -1.65
     ]
    -1.61
    ]>
    -1.60
    >`
    -1.59
     volunteers
    -1.55
    ľ
    -1.51
    IGH
    -1.50
    POSITIVE LOGITS
    ably
    1.84
     mode
    1.78
    shot
    1.75
    agraph
    1.67
    picture
    1.66
    sheet
    1.63
    iative
    1.61
    esan
    1.60
    erne
    1.59
    stock
    1.58
    Activations Density 0.077%

    No Known Activations