© 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. 25402
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reflect" and its variations

    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
    376
    +0.26
    1.5%
    156
    +0.13
    0.7%
    221
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.26
    0.01
    411
    +0.13
    0.01
    127
    +0.11
    0.01
    Negative Logits
    shire
    -1.65
    ielsen
    -1.64
    llo
    -1.61
    rives
    -1.61
    blockList
    -1.55
    ubert
    -1.54
    unction
    -1.53
    lla
    -1.51
    ares
    -1.48
     measure
    -1.45
    POSITIVE LOGITS
     responsibility
    1.54
    initis
    1.42
    heavy
    1.41
     democracy
    1.40
    underbrace
    1.40
     heavy
    1.37
    ¿
    1.36
     ownership
    1.28
    inel
    1.28
    cule
    1.28
    Activations Density 0.019%

    No Known Activations