© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25010
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods and commas, indicating a focus on sentence structure or separation

    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
    156
    +0.22
    1.2%
    373
    +0.14
    0.8%
    234
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    467
    +0.22
    0.02
    50
    +0.14
    0.01
    368
    +0.12
    0.01
    Negative Logits
    rst
    -1.53
    ^](#
    -1.43
    urity
    -1.35
    ît
    -1.34
    ility
    -1.31
    alities
    -1.29
    ticos
    -1.29
    ões
    -1.29
    wers
    -1.29
    ÅĪ
    -1.27
    POSITIVE LOGITS
    own
    1.58
    eed
    1.32
     east
    1.31
     invasion
    1.31
    Ļª
    1.30
     DOT
    1.30
    coming
    1.29
    blic
    1.28
     compromise
    1.26
    owing
    1.26
    Activations Density 0.716%

    No Known Activations