© 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. 22618
    Prev
    Next
    INDEX
    Explanations

    repeated elements, particularly those related to structured data types or programming concepts

    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
    23
    +0.34
    2.0%
    326
    +0.12
    0.7%
    271
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.34
    0.10
    458
    +0.12
    0.10
    326
    +0.12
    0.05
    Negative Logits
    heets
    -1.99
    naire
    -1.89
    velopment
    -1.80
    ressor
    -1.76
    nier
    -1.76
    "}](#
    -1.75
    #.
    -1.63
    ensis
    -1.60
    icles
    -1.58
    liga
    -1.55
    POSITIVE LOGITS
    ogly
    1.70
     bree
    1.63
    ķ
    1.55
     taste
    1.53
     breath
    1.50
     toast
    1.47
    ĻĤ
    1.46
     swallow
    1.46
     turn
    1.45
    woke
    1.44
    Activations Density 1.211%

    No Known Activations