© 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. 25413
    Prev
    Next
    INDEX
    Explanations

    references to the act of reminding

    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
    +0.15
    0.8%
    115
    +0.13
    0.7%
    72
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.15
    0.01
    72
    +0.13
    0.01
    386
    +0.12
    0.01
    Negative Logits
    hene
    -1.63
     agree
    -1.45
    ---|---
    -1.44
    hips
    -1.41
    ]{};
    -1.39
     vers
    -1.37
    aliana
    -1.36
    AU
    -1.35
    hey
    -1.34
    hire
    -1.31
    POSITIVE LOGITS
    ł
    1.77
    estock
    1.60
    atics
    1.58
    ety
    1.55
    indows
    1.54
    obacterium
    1.50
    entary
    1.49
    eting
    1.48
    ership
    1.48
    stress
    1.47
    Activations Density 0.120%

    No Known Activations