© 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. 31085
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'w' as a significant character in text

    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
    306
    +0.12
    0.6%
    410
    +0.11
    0.6%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.12
    0.05
    306
    +0.11
    0.04
    313
    +0.11
    0.04
    Negative Logits
    ancer
    -1.90
    ances
    -1.82
    ance
    -1.66
    oise
    -1.64
    lass
    -1.58
    lasses
    -1.57
    estion
    -1.57
    rance
    -1.49
     pictured
    -1.44
     said
    -1.44
    POSITIVE LOGITS
    fn
    1.59
    arts
    1.52
    ilee
    1.45
     forensic
    1.45
    abi
    1.43
    grant
    1.43
    äng
    1.38
    arming
    1.37
    enders
    1.37
    elcome
    1.36
    Activations Density 0.319%

    No Known Activations