© 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 EvalsExportsinterp-engineNEWAPI 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. 28101
    Prev
    Next
    INDEX
    Explanations

    references to illicit drugs, particularly cocaine

    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
    156
    +0.24
    1.4%
    422
    +0.13
    0.8%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.24
    0.01
    453
    +0.13
    0.01
    63
    +0.11
    0.01
    Negative Logits
    ĥ½
    -2.35
    ĭ
    -2.04
    Ķ
    -2.01
    ·
    -1.99
    į
    -1.92
    ľĵ
    -1.90
    ¯
    -1.88
    Ļª
    -1.87
    -1.85
    ↵
    -1.85
    POSITIVE LOGITS
    caster
    1.80
    break
    1.63
    amount
    1.51
    ([
    1.51
    ulence
    1.49
    works
    1.49
    acters
    1.46
    osity
    1.45
    ulent
    1.44
     amount
    1.43
    Activations Density 0.013%

    No Known Activations