© 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 EvalsExportsinterp-engineNEWAPI 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. 26660
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Durant"

    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
    369
    +0.16
    0.9%
    338
    +0.12
    0.7%
    59
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.16
    0.01
    338
    +0.12
    0.01
    59
    +0.12
    0.01
    Negative Logits
     particular
    -1.64
    compan
    -1.51
    tet
    -1.48
     deletion
    -1.45
    usterity
    -1.42
     adhesion
    -1.41
     sudden
    -1.40
    urred
    -1.39
    USY
    -1.39
     specific
    -1.39
    POSITIVE LOGITS
    ĻĤ
    1.83
    ian
    1.71
    thouse
    1.69
    rant
    1.69
    ©
    1.67
    ģ
    1.60
    ango
    1.59
    ¸
    1.53
    Ĵ
    1.53
    azzo
    1.50
    Activations Density 0.017%

    No Known Activations