© 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. 29805
    Prev
    Next
    INDEX
    Explanations

    references to census data

    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
    71
    +0.17
    0.9%
    442
    +0.14
    0.8%
    117
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.17
    0.02
    26
    +0.14
    0.01
    131
    +0.12
    0.01
    Negative Logits
    ¶
    -5.05
    ı
    -5.04
    ĭ
    -5.03
    ½
    -5.01
    ³
    -5.00
    ¯
    -4.95
    -4.94
     ↵
    -4.94
    -4.94
               ↵
    -4.94
    POSITIVE LOGITS
    illac
    1.70
     survey
    1.57
    rowser
    1.54
    TAG
    1.54
    ITAL
    1.51
    ERTY
    1.49
    estry
    1.49
    AndroidRuntime
    1.47
    annon
    1.46
    ennial
    1.45
    Activations Density 0.108%

    No Known Activations