© 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. 30843
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "undergone" or "witnessed" to indicate significant events or changes

    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
    148
    +0.16
    0.9%
    376
    +0.14
    0.8%
    29
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.16
    0.04
    169
    +0.14
    0.03
    310
    +0.14
    0.04
    Negative Logits
    lands
    -1.76
    feld
    -1.58
    ursed
    -1.49
    )$-
    -1.48
    MOESM
    -1.47
     screened
    -1.43
    hed
    -1.39
    unnumbered
    -1.37
    hurst
    -1.30
    urs
    -1.30
    POSITIVE LOGITS
    ör
    1.55
    oufl
    1.41
    ixon
    1.41
     Boltzmann
    1.39
    ept
    1.38
    enna
    1.37
    antom
    1.35
     missing
    1.34
    plit
    1.32
     quenching
    1.32
    Activations Density 1.098%

    No Known Activations