© 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. 2-RES-SM
    11. 31057
    Prev
    Next
    INDEX
    Explanations

    specific terms related to community or social events and gatherings

    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
    156
    +0.19
    1.1%
    56
    +0.12
    0.7%
    64
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.19
    -0.03
    366
    +0.12
    0.07
    56
    +0.12
    -0.04
    Negative Logits
    ģ
    -2.08
    ĸ
    -1.91
    Ĥ¬
    -1.80
    ĥ
    -1.79
    ¯
    -1.79
    Ľ
    -1.73
    Īĺ
    -1.70
    Ħ
    -1.70
    Ļª
    -1.68
     respectively
    -1.66
    POSITIVE LOGITS
    terday
    2.02
    rbrack
    1.72
    ADVERTISEMENT
    1.71
    onday
    1.62
     Tomorrow
    1.53
    cester
    1.52
    ↵↵↵↵↵↵↵↵
    1.49
     progress
    1.44
    orie
    1.42
    "]
    1.41
    Activations Density 1.780%

    No Known Activations