© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22469
    Prev
    Next
    INDEX
    Explanations

    mentions of specific dates

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    472
    +0.12
    0.7%
    108
    +0.11
    0.6%
    254
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.12
    0.03
    472
    +0.11
    0.03
    304
    +0.11
    0.02
    Negative Logits
    ĻĤ
    -4.61
    Īĺ
    -3.90
    ↵
    -3.87
    ↵
    -3.87
    -3.87
    ↵
    -3.87
    <|outofrange|>
    -3.87
    ↵
    -3.87
    ↵
    -3.87
    ↵        ↵
    -3.87
    POSITIVE LOGITS
    itals
    1.77
    ies
    1.72
    ivia
    1.70
    ÃŃas
    1.59
    bies
    1.58
    powers
    1.58
    verts
    1.56
    endas
    1.55
    uras
    1.54
    ias
    1.54
    Activations Density 0.161%

    No Known Activations