© 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. 31061
    Prev
    Next
    INDEX
    Explanations

    references to settlements and related concepts

    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
    15
    +0.15
    0.8%
    58
    +0.11
    0.6%
    128
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.15
    0.01
    15
    +0.11
    0.01
    180
    +0.10
    0.01
    Negative Logits
     Majority
    -1.60
    tails
    -1.53
     landed
    -1.49
    asses
    -1.46
    spir
    -1.44
    itte
    -1.42
    ¿½
    -1.36
    IBILITY
    -1.33
     consequence
    -1.31
    agers
    -1.31
    POSITIVE LOGITS
    heet
    2.01
    creen
    1.89
    uit
    1.79
    erver
    1.70
    iedad
    1.67
    ocial
    1.66
    ensor
    1.64
    ima
    1.62
    weet
    1.58
     msgid
    1.55
    Activations Density 0.052%

    No Known Activations