© 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. 23652
    Prev
    Next
    INDEX
    Explanations

    definite articles and demonstrative pronouns

    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
    323
    +0.11
    0.6%
    69
    +0.11
    0.6%
    82
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.11
    0.01
    125
    +0.11
    0.01
    179
    +0.11
    0.01
    Negative Logits
    amines
    -1.72
    protect
    -1.60
    $.[]{
    -1.48
    ÑıÑĤ
    -1.39
     simpl
    -1.37
     conservation
    -1.36
    ""
    -1.30
     my
    -1.28
     Native
    -1.23
    pping
    -1.23
    POSITIVE LOGITS
    Īĺ
    2.71
    2.60
    ↵
    2.60
    ↵↵
    2.60
    <|outofrange|>
    2.60
    <|padding|>
    2.60
    2.60
    2.60
                ↵
    2.60
    <|outofrange|>
    2.60
    Activations Density 0.036%

    No Known Activations