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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27761
    Prev
    Next
    INDEX
    Explanations

    repeated articles, specifically 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/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
    417
    +0.12
    0.7%
    225
    +0.12
    0.6%
    341
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.12
    0.47
    98
    +0.12
    0.21
    228
    +0.11
    0.32
    Negative Logits
    rael
    -1.67
    lut
    -1.66
    ubert
    -1.55
    iet
    -1.53
    ieu
    -1.52
    "?"
    -1.51
    oun
    -1.51
    rier
    -1.49
    ruction
    -1.49
    ouden
    -1.48
    POSITIVE LOGITS
     precedent
    1.58
     GENERATED
    1.51
     MSS
    1.40
    Simplify
    1.37
    icity
    1.37
     older
    1.36
    PM
    1.35
    psin
    1.32
     fain
    1.31
     [(\[
    1.31
    Activations Density 2.906%

    No Known Activations