© 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. 2-MLP-SM
    11. 22663
    Prev
    Next
    INDEX
    Explanations

    references to specific days and months

    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
    223
    +0.16
    0.9%
    174
    +0.13
    0.7%
    163
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.16
    0.04
    334
    +0.13
    0.04
    174
    +0.13
    0.04
    Negative Logits
    ths
    -1.46
     mile
    -1.42
     miles
    -1.39
     cigarettes
    -1.35
     road
    -1.33
     bike
    -1.33
     Jefferson
    -1.33
     contrary
    -1.32
     satisfaction
    -1.32
     obstacles
    -1.32
    POSITIVE LOGITS
    phosphate
    1.50
    py
    1.42
    icar
    1.37
    mosp
    1.35
    ]{.
    1.35
     -*-
    1.35
    ASP
    1.32
    ernel
    1.32
    \-
    1.32
    mann
    1.31
    Activations Density 0.276%

    No Known Activations