© 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. 28477
    Prev
    Next
    INDEX
    Explanations

    references to the drug methamphetamine and related terms

    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
    2
    +0.16
    0.9%
    356
    +0.13
    0.8%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.16
    0.01
    356
    +0.13
    0.01
    0
    +0.12
    0.01
    Negative Logits
    ´
    -3.31
    ķ
    -3.22
    ĸ´
    -3.16
    ·¸
    -3.13
    ľ
    -3.13
    ĩ
    -3.11
    Ĭ
    -3.10
    ¿
    -3.06
    °
    -3.01
    ĨĴ
    -2.93
    POSITIVE LOGITS
    :`
    1.93
    rooms
    1.85
    -,
    1.76
     -,
    1.72
    wig
    1.62
    chap
    1.60
    minded
    1.59
    room
    1.59
    enium
    1.58
    quarter
    1.57
    Activations Density 0.006%

    No Known Activations