© 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. 2-MLP-SM
    11. 26016
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in."

    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
    156
    +0.21
    1.2%
    313
    +0.13
    0.7%
    17
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.21
    0.05
    454
    +0.13
    0.03
    44
    +0.11
    0.03
    Negative Logits
    ocene
    -1.91
     parameter
    -1.54
     to
    -1.48
     hypothesis
    -1.43
     turn
    -1.42
     casc
    -1.40
    ks
    -1.38
     await
    -1.36
    zzi
    -1.35
     increments
    -1.31
    POSITIVE LOGITS
    Ļª
    2.55
    ĻĤ
    2.37
    Īĺ
    2.25
    ĨĴ
    1.93
    ı
    1.80
    »¿
    1.67
    ĭ
    1.64
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    1.63
    .”).
    1.57
    ±
    1.54
    Activations Density 0.422%

    No Known Activations