© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 10439
    Prev
    Next
    INDEX
    Explanations

    colon-separated values in structured 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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    369
    +0.17
    0.9%
    497
    +0.15
    0.8%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.17
    0.02
    129
    +0.15
    -0.00
    410
    +0.14
    0.04
    Negative Logits
    ipore
    -1.99
    uxe
    -1.79
    era
    -1.75
    otypes
    -1.69
    oplast
    -1.66
     (\~
    -1.61
     extinction
    -1.61
    plasty
    -1.59
    oidal
    -1.58
    ga
    -1.54
    POSITIVE LOGITS
     comments
    1.62
     mention
    1.56
     Prospect
    1.49
     Proceedings
    1.48
     amazed
    1.45
     Redistributions
    1.44
     references
    1.40
     Chr
    1.39
     Editor
    1.38
     conversation
    1.36
    Activations Density 0.292%

    No Known Activations