© 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. 26349
    Prev
    Next
    INDEX
    Explanations

    descriptions related to smell

    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
    494
    +0.15
    0.9%
    376
    +0.13
    0.8%
    100
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.15
    0.02
    494
    +0.13
    0.01
    301
    +0.12
    0.01
    Negative Logits
    pless
    -1.59
    unnumbered
    -1.58
    verte
    -1.54
    ¸
    -1.51
    ureus
    -1.45
    ¼
    -1.41
    ople
    -1.41
     Ski
    -1.40
    rap
    -1.39
    ção
    -1.38
    POSITIVE LOGITS
    manship
    2.13
    iest
    2.00
    ings
    1.89
    liner
    1.62
    bilt
    1.57
    ivist
    1.57
     like
    1.57
    less
    1.57
    bridge
    1.56
    etic
    1.55
    Activations Density 0.014%

    No Known Activations