© 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. 31835
    Prev
    Next
    INDEX
    Explanations

    words related to athletic achievements and participation in sports

    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
    +0.16
    0.9%
    459
    +0.13
    0.7%
    258
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.16
    0.09
    73
    +0.13
    0.05
    174
    +0.12
    0.09
    Negative Logits
    Ĵ
    -5.22
    ī
    -5.16
    ↵↵
    -4.97
    -4.97
    -4.97
    -4.97
    ↵↵
    -4.97
    čč
    -4.97
          ↵
    -4.97
    ↵↵
    -4.97
    POSITIVE LOGITS
    ship
    2.43
    who
    1.95
    chief
    1.84
    jee
    1.84
    geant
    1.84
    ships
    1.82
     whom
    1.70
    friends
    1.69
     who
    1.68
    leader
    1.65
    Activations Density 1.414%

    No Known Activations