© 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. 4-RES-SM
    11. 13180
    Prev
    Next
    INDEX
    Explanations

    references to specific products and their qualities

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    146
    +0.14
    0.8%
    292
    +0.12
    0.7%
    297
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.53
    156
    +0.12
    0.37
    71
    +0.12
    0.37
    Negative Logits
     microbi
    -1.94
     virulence
    -1.94
     spores
    -1.84
     Tas
    -1.82
     Marl
    -1.75
     MRSA
    -1.69
     glac
    -1.68
    CoV
    -1.67
     SARS
    -1.66
     outbreaks
    -1.65
    POSITIVE LOGITS
     jQuery
    4.61
     jquery
    4.03
    jQuery
    3.97
    jquery
    3.69
     Ajax
    3.61
     ajax
    3.60
     AJ
    3.33
    ajax
    3.05
     DOM
    2.97
     javascript
    2.93
    Activations Density 0.906%

    No Known Activations