© 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. 29973
    Prev
    Next
    INDEX
    Explanations

    instances of the word "submitted."

    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
    376
    +0.26
    1.5%
    69
    +0.12
    0.7%
    443
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.26
    0.01
    443
    +0.12
    0.01
    423
    +0.12
    0.01
    Negative Logits
    ishly
    -1.76
    )](#
    -1.67
    rsquo
    -1.52
    rained
    -1.51
    east
    -1.44
    ))$.
    -1.42
     Appeals
    -1.41
    unnumbered
    -1.39
    called
    -1.38
     JavaScript
    -1.35
    POSITIVE LOGITS
    imental
    1.81
    ató
    1.65
    ĻĤ
    1.65
     defeats
    1.62
    etting
    1.54
     receipts
    1.52
    cule
    1.49
    rag
    1.48
    ilant
    1.47
    pone
    1.47
    Activations Density 0.012%

    No Known Activations