© 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 EvalsExportsAPI 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. 28945
    Prev
    Next
    INDEX
    Explanations

    the word "man."

    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
    +0.16
    0.9%
    197
    +0.12
    0.7%
    477
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.16
    0.04
    107
    +0.12
    0.03
    475
    +0.12
    0.03
    Negative Logits
     suppose
    -1.65
     Africans
    -1.54
     sexes
    -1.51
     Jews
    -1.50
    ÑģÑĤÑĮ
    -1.47
    ffen
    -1.47
    Americans
    -1.45
     Palin
    -1.45
    ...?"
    -1.43
     mothers
    -1.43
    POSITIVE LOGITS
    uscript
    2.70
    hattan
    2.35
    agment
    2.19
    agem
    2.00
    ifest
    1.97
    hole
    1.90
    ifold
    1.89
    oj
    1.88
    ufact
    1.82
    ita
    1.81
    Activations Density 0.098%

    No Known Activations