© 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. 26024
    Prev
    Next
    INDEX
    Explanations

    references to unpleasant smells or odors

    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
    59
    +0.16
    0.9%
    113
    +0.14
    0.8%
    12
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.16
    0.01
    287
    +0.14
    0.01
    114
    +0.14
    0.01
    Negative Logits
    TRODUCTION
    -1.69
    orget
    -1.64
    >();
    -1.57
     albumin
    -1.55
    >`
    -1.45
    TES
    -1.38
    apine
    -1.38
    ubicin
    -1.38
    Zip
    -1.33
    uclear
    -1.33
    POSITIVE LOGITS
    ī
    2.47
    Ģ
    2.41
    ¥
    2.39
    ®
    2.29
    ľ
    2.20
    ł
    2.19
    º
    2.13
    ±
    2.06
    ¹
    2.05
    İ
    2.04
    Activations Density 0.323%

    No Known Activations