© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25280
    Prev
    Next
    INDEX
    Explanations

    terms related to arthritis and inflammatory conditions

    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
    +0.21
    1.3%
    315
    +0.15
    0.9%
    184
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.21
    0.01
    184
    +0.15
    0.01
    159
    +0.15
    0.01
    Negative Logits
    ı
    -1.75
    >(
    -1.50
    aines
    -1.50
     vez
    -1.48
    qn
    -1.45
     heterosexual
    -1.44
    ¿½
    -1.43
    ateurs
    -1.43
    ometh
    -1.43
     mates
    -1.42
    POSITIVE LOGITS
    stalk
    1.94
    istine
    1.51
    itage
    1.44
    nament
    1.42
    istor
    1.38
     (,
    1.36
    hell
    1.36
    nikov
    1.35
    break
    1.35
    round
    1.34
    Activations Density 0.007%

    No Known Activations