© 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. 2-MLP-SM
    11. 23732
    Prev
    Next
    INDEX
    Explanations

    information related to women's health issues and access to healthcare services

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    156
    +0.14
    0.8%
    169
    +0.14
    0.8%
    127
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.14
    0.10
    335
    +0.14
    0.09
    155
    +0.11
    0.09
    Negative Logits
    thood
    -1.64
     deaths
    -1.52
    archy
    -1.49
     League
    -1.41
     tons
    -1.40
     relapse
    -1.39
    ĵ
    -1.38
    ĥ½
    -1.35
     fluct
    -1.35
     injuries
    -1.32
    POSITIVE LOGITS
    tron
    1.53
    stated
    1.41
    âĢŁ
    1.41
    ieurs
    1.40
    liness
    1.40
    statement
    1.39
     illustrated
    1.38
    :`
    1.36
     arrangement
    1.36
    "|
    1.33
    Activations Density 1.304%

    No Known Activations