© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25837
    Prev
    Next
    INDEX
    Explanations

    instances of the word "called"

    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
    91
    +0.12
    0.7%
    142
    +0.12
    0.6%
    169
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.12
    0.04
    502
    +0.12
    0.03
    97
    +0.11
    0.02
    Negative Logits
     myself
    -2.03
    ements
    -1.74
     past
    -1.73
     periods
    -1.55
     newsletters
    -1.50
     purposes
    -1.48
     spices
    -1.46
    ard
    -1.45
     forth
    -1.45
     my
    -1.44
    POSITIVE LOGITS
    levard
    1.82
    sembl
    1.62
     Act
    1.50
    documentclass
    1.46
    ))$,
    1.45
    enties
    1.44
    **),
    1.43
    negie
    1.43
     Li
    1.42
    rij
    1.40
    Activations Density 0.157%

    No Known Activations