© 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. 4-RES-SM
    11. 9250
    Prev
    Next
    INDEX
    Explanations

    weather-related phenomena and their impacts

    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
    30
    +0.12
    0.6%
    186
    +0.11
    0.6%
    243
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.12
    0.02
    395
    +0.11
    0.07
    510
    +0.11
    0.12
    Negative Logits
     oligonucleotide
    -1.65
     associative
    -1.64
     ethical
    -1.61
     privileges
    -1.61
     penis
    -1.59
     oligonucleotides
    -1.59
     cloning
    -1.58
    obby
    -1.58
     laparoscopic
    -1.55
     Juda
    -1.54
    POSITIVE LOGITS
     storms
    3.84
     hurricane
    3.71
     weather
    3.67
     meteor
    3.66
     Weather
    3.59
     rainfall
    3.57
     rain
    3.49
    weather
    3.40
     forecast
    3.38
     storm
    3.34
    Activations Density 2.531%

    No Known Activations