© 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. 13526
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the significance or importance of roles in various contexts, particularly in research or organizational settings

    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
    78
    +0.24
    1.5%
    21
    +0.17
    1.1%
    348
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.24
    0.04
    184
    +0.17
    0.03
    198
    +0.14
    0.03
    Negative Logits
    »¿
    -3.50
    ĸ´
    -2.97
    ĥ½
    -2.89
    µ
    -2.83
    ľĵ
    -2.72
    -2.71
    -2.71
    ↵
    -2.71
    ↵↵
    -2.71
    -2.71
    POSITIVE LOGITS
     in
    1.74
     downstream
    1.71
     elsewhere
    1.68
     therein
    1.67
     role
    1.61
     mediating
    1.58
     during
    1.57
     throughout
    1.57
     whatsoever
    1.54
    .^[@
    1.50
    Activations Density 0.157%

    No Known Activations