© 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. 2-RES-SM
    11. 30061
    Prev
    Next
    INDEX
    Explanations

    sentiments related to community gatherings and positive shared experiences

    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
    56
    +0.21
    1.2%
    263
    +0.16
    0.9%
    319
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.21
    0.17
    56
    +0.16
    -0.02
    130
    +0.11
    0.20
    Negative Logits
    ģ
    -3.42
    Ļª
    -3.38
    ħ
    -3.29
    Ĥ¬
    -3.27
    ł
    -3.23
    ĥ
    -3.21
    ¯
    -3.16
    ŀ
    -3.16
    ¿½
    -3.13
    «
    -3.13
    POSITIVE LOGITS
     ðŁĻĤ
    1.85
     ðŁĺ
    1.75
    blogger
    1.71
    Submitted
    1.71
     luck
    1.65
     finished
    1.61
    ************************************************************************
    1.56
     wow
    1.55
     LOVE
    1.53
    ****************************************************************
    1.52
    Activations Density 5.483%

    No Known Activations