© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 26948
    Prev
    Next
    INDEX
    Explanations

    references to biological rhythms and menstrual health

    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
    156
    +0.35
    2.1%
    148
    +0.13
    0.8%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.35
    0.01
    156
    +0.13
    0.01
    111
    +0.12
    0.01
    Negative Logits
    urop
    -1.47
    chanical
    -1.43
    ctin
    -1.40
     definite
    -1.37
    ween
    -1.33
     Theoretical
    -1.31
    aliana
    -1.26
     Available
    -1.25
    %=
    -1.22
    zzo
    -1.22
    POSITIVE LOGITS
    shots
    1.69
    azine
    1.65
     footsteps
    1.54
    othet
    1.53
    ¥
    1.51
    shit
    1.46
    stalk
    1.46
    ette
    1.45
     rhythm
    1.39
     sucks
    1.39
    Activations Density 0.010%

    No Known Activations