© 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. Residuals
    9. 1-RES-SM
    11. 24094
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to demonstrating or establishing proof or validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    376
    +0.17
    0.9%
    115
    +0.13
    0.7%
    118
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    118
    +0.17
    0.02
    72
    +0.13
    0.02
    38
    +0.12
    0.02
    Negative Logits
    ¦
    -1.92
    ¡
    -1.81
    ¢
    -1.74
    amaz
    -1.72
    à±ģ
    -1.65
    ij
    -1.64
    burst
    -1.62
    ricular
    -1.60
    rist
    -1.58
    ¥
    -1.57
    POSITIVE LOGITS
    edly
    1.75
     hell
    1.51
     fruitful
    1.43
     adul
    1.42
     torture
    1.42
     correctness
    1.41
     miracles
    1.41
     mortar
    1.41
     false
    1.40
     colitis
    1.39
    Activations Density 0.091%

    No Known Activations