© 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. 2-MLP-SM
    11. 23826
    Prev
    Next
    INDEX
    Explanations

    specific mentions of sequences in biological contexts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    58
    +0.15
    0.9%
    333
    +0.12
    0.7%
    14
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.15
    0.03
    341
    +0.12
    0.03
    23
    +0.11
    0.01
    Negative Logits
    ?).
    -1.73
    )?
    -1.73
    ches
    -1.62
    tees
    -1.60
     should
    -1.56
    ively
    -1.55
     sexes
    -1.52
    mapsto
    -1.50
    acters
    -1.48
     sides
    -1.47
    POSITIVE LOGITS
    ight
    1.41
    :_
    1.39
     merchant
    1.35
     Rhode
    1.34
     .
    1.32
     Stock
    1.31
     Light
    1.30
    isance
    1.27
     gratitude
    1.20
     youth
    1.20
    Activations Density 0.326%

    No Known Activations