© 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. 23526
    Prev
    Next
    INDEX
    Explanations

    terms related to geographic locations and conditions

    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
    104
    +0.14
    0.8%
    378
    +0.12
    0.7%
    340
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.14
    0.01
    454
    +0.12
    0.00
    340
    +0.11
    0.00
    Negative Logits
    documentclass
    -1.63
    PORT
    -1.40
    forge
    -1.35
    aber
    -1.35
    'd
    -1.33
    blast
    -1.33
     specimens
    -1.29
    otal
    -1.28
    msgstr
    -1.28
    actin
    -1.27
    POSITIVE LOGITS
    gage
    1.52
    hest
    1.52
    ny
    1.51
     etc
    1.45
    rez
    1.38
     merger
    1.37
     Lakers
    1.36
    ramento
    1.35
     mergers
    1.35
    inations
    1.35
    Activations Density 0.096%

    No Known Activations