© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 26949
    Prev
    Next
    INDEX
    Explanations

    references to herbs and herbal products

    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
    407
    +0.11
    0.6%
    148
    +0.10
    0.6%
    43
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.11
    0.01
    401
    +0.10
    0.01
    43
    +0.10
    0.01
    Negative Logits
    Ļª
    -1.53
     gay
    -1.44
     où
    -1.42
    CHAPTER
    -1.41
     '</
    -1.34
     different
    -1.32
     welcome
    -1.29
     descent
    -1.28
    Ħ
    -1.28
    ĺ
    -1.28
    POSITIVE LOGITS
    erals
    2.12
    isan
    1.93
    amount
    1.70
    icides
    1.70
    fors
    1.63
    ophilic
    1.63
    idor
    1.61
    notes
    1.61
    grow
    1.61
    imeter
    1.59
    Activations Density 0.017%

    No Known Activations