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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27073
    Prev
    Next
    INDEX
    Explanations

    instances of the word "we."

    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
    +0.14
    0.8%
    489
    +0.14
    0.8%
    26
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.14
    0.11
    184
    +0.14
    0.10
    138
    +0.12
    0.09
    Negative Logits
    olev
    -1.67
    vet
    -1.48
    ivent
    -1.46
    dy
    -1.45
     past
    -1.43
    esta
    -1.43
     finally
    -1.42
    IPE
    -1.42
    agus
    -1.40
    uca
    -1.38
    POSITIVE LOGITS
    ħ
    2.67
    ¡
    2.65
    ł
    2.57
    ĺ
    2.46
    ģ
    2.45
    »
    2.42
    Ĵ
    2.37
    £
    2.36
    Ł
    2.34
    ĥ½
    2.32
    Activations Density 0.169%

    No Known Activations