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

    Neuronpedia

    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. 1-RES-SM
    11. 26685
    Prev
    Next
    INDEX
    Explanations

    references to authors and their affiliations in academic or legal contexts

    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
    391
    +0.12
    0.7%
    478
    +0.12
    0.7%
    181
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.12
    0.07
    391
    +0.12
    0.05
    203
    +0.12
    0.07
    Negative Logits
    ¹
    -2.47
    ¬
    -2.44
    ª
    -2.40
    »
    -2.37
    Ĺ
    -2.36
    ¦
    -2.33
    Ł
    -2.33
    ĺ
    -2.23
    ģ
    -2.22
    ¢
    -2.21
    POSITIVE LOGITS
    ologie
    1.87
    ologia
    1.61
     Principles
    1.54
     nature
    1.51
     conclusion
    1.50
     principles
    1.50
    aphys
    1.50
     Anal
    1.48
    )]{}
    1.47
     interpretations
    1.47
    Activations Density 0.985%

    No Known Activations