© 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. 22672
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic mutations

    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
    371
    +0.11
    0.6%
    156
    +0.11
    0.6%
    122
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.11
    0.01
    361
    +0.11
    0.02
    458
    +0.11
    0.01
    Negative Logits
    Ĩ
    -2.28
    ¤
    -2.16
    Ĺ
    -2.05
    ł
    -2.01
    ¥
    -1.97
    ľĵ
    -1.92
    ŀ
    -1.90
    ĻĤ
    -1.89
    ħ
    -1.83
    ↵
    -1.80
    POSITIVE LOGITS
    athed
    1.76
    '."
    1.57
    ED
    1.51
    ade
    1.48
    ème
    1.44
     optionally
    1.38
    "."
    1.37
     deleg
    1.36
     adapted
    1.35
     esp
    1.32
    Activations Density 0.133%

    No Known Activations