© 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. 2-MLP-SM
    11. 22742
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

    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
    441
    +0.11
    0.6%
    121
    +0.11
    0.6%
    506
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.11
    0.08
    314
    +0.11
    0.07
    441
    +0.11
    0.06
    Negative Logits
     faith
    -1.58
     âĢķ
    -1.50
    ison
    -1.47
     fallen
    -1.40
    TRODUCTION
    -1.40
    oll
    -1.40
     risen
    -1.39
    ux
    -1.39
    ptions
    -1.36
    crets
    -1.30
    POSITIVE LOGITS
    <|outofrange|>
    5.53
    <|outofrange|>
    5.53
    <|outofrange|>
    5.53
    ↵↵
    5.53
    <|outofrange|>
    5.53
    ↵
    5.53
    5.53
    ↵  âĢĥ
    5.53
    ↵
    5.53
    5.53
    Activations Density 0.633%

    No Known Activations