© 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. 26639
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "be sure."

    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
    456
    +0.14
    0.8%
    451
    +0.12
    0.7%
    116
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    456
    +0.14
    0.01
    326
    +0.12
    0.01
    364
    +0.12
    0.02
    Negative Logits
     ever
    -1.47
    ypse
    -1.39
     whatsoever
    -1.36
    ureus
    -1.34
     ABS
    -1.33
     deserve
    -1.31
    releases
    -1.29
    enron
    -1.29
     lately
    -1.27
     efforts
    -1.27
    POSITIVE LOGITS
    ķ
    2.82
    Ŀ
    2.66
    ij
    2.60
    ŀ
    2.51
    ł
    2.50
    ¹
    2.50
    ¡
    2.37
    ļ
    2.36
    ģ
    2.35
    Ĥ
    2.33
    Activations Density 0.177%

    No Known Activations