© 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. 30941
    Prev
    Next
    INDEX
    Explanations

    directional indicators related to geographic locations

    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
    81
    +0.14
    0.8%
    438
    +0.14
    0.8%
    362
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.14
    0.01
    64
    +0.14
    0.01
    459
    +0.13
    0.01
    Negative Logits
    ostat
    -1.79
    arner
    -1.59
    verage
    -1.56
    areness
    -1.50
    eter
    -1.48
    akin
    -1.46
    urer
    -1.45
    urations
    -1.42
    gers
    -1.41
    asure
    -1.41
    POSITIVE LOGITS
    »¿
    3.83
    Ł
    3.76
    Ļª
    3.72
    ¸
    3.67
    ł
    3.62
    ²
    3.55
    3.53
    ↵
    3.53
    ↵
    3.53
    ↵
    3.53
    Activations Density 0.425%

    No Known Activations