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

    Neuronpedia

    Jacobian LensNEW
    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. 28730
    Prev
    Next
    INDEX
    Explanations

    references to PET (polyethylene terephthalate) packaging

    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
    369
    +0.18
    1.0%
    148
    +0.14
    0.8%
    219
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.18
    0.01
    65
    +0.14
    0.01
    351
    +0.14
    0.01
    Negative Logits
    Ļª
    -1.64
    Ķ
    -1.61
     sudden
    -1.59
     else
    -1.58
     smaller
    -1.58
    »
    -1.47
    oxacin
    -1.47
    fluence
    -1.46
     different
    -1.46
    oming
    -1.46
    POSITIVE LOGITS
    ITION
    1.82
    FC
    1.78
    sci
    1.59
    ERS
    1.58
    )",
    1.57
     relies
    1.55
    IENT
    1.55
    STA
    1.52
    ilent
    1.52
    )&
    1.50
    Activations Density 1.576%

    No Known Activations