© 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. 31064
    Prev
    Next
    INDEX
    Explanations

    keywords indicating positional or configuration 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
    376
    +0.12
    0.7%
    81
    +0.11
    0.6%
    2
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.12
    0.02
    275
    +0.11
    0.02
    459
    +0.10
    0.02
    Negative Logits
    rian
    -1.72
     magnitude
    -1.66
     yours
    -1.58
    »¿
    -1.57
     plain
    -1.57
    §
    -1.53
    Ĥ
    -1.52
    uster
    -1.51
    ellow
    -1.50
    rians
    -1.50
    POSITIVE LOGITS
    itives
    2.03
    etable
    1.87
    quito
    1.83
    endor
    1.74
    izione
    1.68
    pad
    1.64
    aku
    1.63
    ÃŃf
    1.63
    iko
    1.63
    cribed
    1.59
    Activations Density 0.138%

    No Known Activations