© 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. 13898
    Prev
    Next
    INDEX
    Explanations

    instances of traffic regulations and enforcement

    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
    501
    +0.19
    1.1%
    306
    +0.15
    0.9%
    307
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.19
    0.03
    64
    +0.15
    0.03
    277
    +0.13
    0.01
    Negative Logits
    ères
    -1.65
    ments
    -1.64
    aurus
    -1.48
    cliffe
    -1.44
    rays
    -1.44
    unners
    -1.42
     herself
    -1.42
    fered
    -1.40
     progresses
    -1.39
    actory
    -1.36
    POSITIVE LOGITS
    Ĩ
    3.70
    ħ
    3.49
    Īĺ
    3.48
    ¹
    3.37
    Į
    3.36
    ī
    3.35
    Ī
    3.33
    ½
    3.30
    ĥ
    3.29
    ģ
    3.11
    Activations Density 0.102%

    No Known Activations