© 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. 0-MLP-SM
    11. 25102
    Prev
    Next
    INDEX
    Explanations

    mentions of websites

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.17
    1.0%
    71
    +0.12
    0.7%
    352
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.17
    0.04
    58
    +0.12
    0.03
    114
    +0.12
    0.03
    Negative Logits
    §
    -1.81
     heart
    -1.66
    öm
    -1.63
    ]>
    -1.56
    ounder
    -1.53
     sudden
    -1.49
    Į
    -1.48
     bowel
    -1.47
     dare
    -1.44
    ĥ½
    -1.43
    POSITIVE LOGITS
    plate
    1.60
    spacing
    1.60
    eno
    1.57
    yards
    1.57
    bed
    1.55
    cias
    1.54
     profile
    1.54
    eries
    1.51
    pieces
    1.50
    AtIndex
    1.48
    Activations Density 0.021%

    No Known Activations