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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 26874
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, particularly related to Iraq

    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
    71
    +0.14
    0.8%
    369
    +0.14
    0.8%
    227
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.14
    0.03
    413
    +0.14
    0.02
    271
    +0.14
    0.01
    Negative Logits
    Ŀ
    -1.75
     '</
    -1.72
     maternal
    -1.65
    į
    -1.63
     wealthy
    -1.51
    '>
    -1.51
     childhood
    -1.47
     supportive
    -1.46
     ich
    -1.44
    Ķ
    -1.44
    POSITIVE LOGITS
    shire
    2.13
     itself
    1.75
     themselves
    1.75
    volt
    1.70
    birds
    1.70
    LINE
    1.67
    isco
    1.56
    ISE
    1.51
    bank
    1.49
    iens
    1.48
    Activations Density 3.580%

    No Known Activations