© 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. 0-MLP-SM
    11. 30938
    Prev
    Next
    INDEX
    Explanations

    instances of the word "amid" and its variations conveying context or circumstances surrounding an event

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    29
    +0.14
    0.8%
    478
    +0.14
    0.8%
    463
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.14
    0.01
    140
    +0.14
    0.01
    231
    +0.12
    0.01
    Negative Logits
    adian
    -1.67
    \%
    -1.50
    HS
    -1.45
    ÅĽÄĩ
    -1.42
    CHO
    -1.42
    LM
    -1.40
    clin
    -1.40
     Licensed
    -1.38
    invasive
    -1.36
    MH
    -1.36
    POSITIVE LOGITS
    ©
    3.67
    ¶
    3.34
    ĻĤ
    3.14
    °
    3.14
    ↵
    2.94
    č↵
    2.94
               ↵
    2.94
    č↵
    2.94
    2.94
    <|outofrange|>
    2.94
    Activations Density 0.014%

    No Known Activations