© 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. 30992
    Prev
    Next
    INDEX
    Explanations

    references to online forums

    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
    335
    +0.12
    0.7%
    476
    +0.12
    0.7%
    264
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.12
    0.01
    264
    +0.12
    0.01
    476
    +0.11
    0.01
    Negative Logits
     morning
    -1.83
     midnight
    -1.77
     same
    -1.73
     gently
    -1.62
     yours
    -1.56
     converse
    -1.55
     randomly
    -1.52
     brow
    -1.52
     suspect
    -1.52
     faint
    -1.51
    POSITIVE LOGITS
    wiki
    2.00
    olta
    2.00
    erate
    1.91
    istas
    1.73
    vist
    1.70
    ematic
    1.70
    ÅĽci
    1.65
    opa
    1.65
    aña
    1.63
    lectual
    1.63
    Activations Density 0.010%

    No Known Activations