© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29017
    Prev
    Next
    INDEX
    Explanations

    numerical information and measurements

    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
    36
    +0.16
    0.9%
    257
    +0.11
    0.6%
    142
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.16
    0.06
    317
    +0.11
    0.07
    436
    +0.11
    0.08
    Negative Logits
    à±ģ
    -1.51
     plaque
    -1.48
     ging
    -1.48
    inary
    -1.44
    àµ
    -1.38
    àµį
    -1.36
    ifi
    -1.33
    igraphy
    -1.32
    enance
    -1.32
    ARRANT
    -1.30
    POSITIVE LOGITS
    ½
    2.37
    Īĺ
    2.28
    ¹
    2.26
    Ŀ
    2.21
     ↵
    2.20
    ↵    ↵
    2.20
    ↵
    2.20
    ↵
    2.20
    2.20
    ↵  ↵
    2.20
    Activations Density 0.624%

    No Known Activations