© 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. 24980
    Prev
    Next
    INDEX
    Explanations

    the conjunction "And" indicating the continuation or addition of information

    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
    478
    +0.18
    1.0%
    209
    +0.14
    0.8%
    144
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.18
    0.06
    209
    +0.14
    0.06
    85
    +0.13
    0.06
    Negative Logits
    backs
    -1.69
     Sear
    -1.47
     about
    -1.45
     chapters
    -1.45
    achers
    -1.43
    ados
    -1.42
     them
    -1.39
     cover
    -1.35
    mining
    -1.35
    mine
    -1.35
    POSITIVE LOGITS
    alus
    2.15
    rea
    1.93
    chitz
    1.93
    rew
    1.86
    rei
    1.83
    ilton
    1.70
    rian
    1.70
    rogens
    1.65
    ré
    1.65
    ¤
    1.63
    Activations Density 0.255%

    No Known Activations