© 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. 25433
    Prev
    Next
    INDEX
    Explanations

    words that relate to various influential elements or considerations in different contexts

    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
    +0.13
    0.8%
    9
    +0.12
    0.7%
    471
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.13
    0.03
    293
    +0.12
    0.02
    471
    +0.10
    0.02
    Negative Logits
    ¿½
    -3.07
    Ĵ
    -2.24
    ¸
    -2.16
    ·
    -2.14
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -2.08
    ´
    -2.08
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -2.03
    ·¸
    -1.97
    ±
    -1.97
    ¾
    -1.96
    POSITIVE LOGITS
    ista
    1.80
    olver
    1.77
    iele
    1.75
     RPG
    1.70
    aline
    1.69
    ikel
    1.66
    loader
    1.66
    orbent
    1.62
    igraph
    1.62
    entry
    1.60
    Activations Density 0.112%

    No Known Activations