© 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 EvalsExportsAPI 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. 11534
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a."

    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
    156
    +0.17
    0.9%
    153
    +0.17
    0.9%
    414
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.17
    0.06
    153
    +0.17
    0.05
    123
    +0.12
    0.04
    Negative Logits
    ¥
    -1.81
    §
    -1.80
    fires
    -1.76
    º
    -1.74
    Īĺ
    -1.74
    ª
    -1.68
    ľĵ
    -1.64
    <|outofrange|>
    -1.64
    -1.64
    č↵
    -1.64
    POSITIVE LOGITS
     consequence
    2.93
     result
    2.80
     whole
    2.43
     means
    2.20
     substitute
    2.18
     basis
    2.02
     predictor
    1.99
     contributor
    1.91
     matter
    1.89
     reminder
    1.81
    Activations Density 0.209%

    No Known Activations