© 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. 22669
    Prev
    Next
    INDEX
    Explanations

    categories and classifications associated with content

    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
    422
    +0.14
    0.8%
    469
    +0.13
    0.7%
    7
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.14
    0.08
    56
    +0.13
    0.11
    469
    +0.12
    0.07
    Negative Logits
     letters
    -1.50
     unders
    -1.45
    heets
    -1.37
     Declaration
    -1.36
    reate
    -1.35
     patient
    -1.33
     (**
    -1.33
     ***
    -1.32
     chr
    -1.32
     letter
    -1.31
    POSITIVE LOGITS
    ¤
    1.91
    §
    1.76
    £
    1.70
    heim
    1.64
    ®
    1.59
     hospitality
    1.59
    heimer
    1.48
    ther
    1.48
    ¯
    1.47
    ÃŃs
    1.45
    Activations Density 2.282%

    No Known Activations