© 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. 31188
    Prev
    Next
    INDEX
    Explanations

    the date "Jun 10."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    59
    +0.16
    0.9%
    369
    +0.16
    0.9%
    52
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.16
    0.01
    111
    +0.16
    0.01
    281
    +0.13
    0.01
    Negative Logits
    upon
    -1.42
     true
    -1.37
     angels
    -1.34
     superior
    -1.33
    true
    -1.27
     poor
    -1.27
     swine
    -1.26
    rien
    -1.25
    Appellee
    -1.24
     nice
    -1.24
    POSITIVE LOGITS
    erals
    1.99
    nals
    1.81
    eno
    1.80
    uel
    1.64
    atype
    1.62
    arate
    1.62
    etable
    1.61
    iani
    1.61
    thal
    1.61
    ieux
    1.58
    Activations Density 0.009%

    No Known Activations