© 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. 1-RES-SM
    11. 25571
    Prev
    Next
    INDEX
    Explanations

    references to Pakistan and its context within various topics

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.21
    1.2%
    71
    +0.17
    1.0%
    421
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.21
    0.05
    156
    +0.17
    0.03
    271
    +0.13
    0.02
    Negative Logits
    ĥ½
    -3.05
    ł
    -2.73
    İ
    -2.70
    ĭ
    -2.69
    Ŀ
    -2.66
    Ĥ
    -2.61
    ¾
    -2.60
    ¶
    -2.55
    ħ
    -2.55
    ī
    -2.53
    POSITIVE LOGITS
    istani
    2.62
    istan
    2.61
    shire
    1.98
    isia
    1.92
    ESE
    1.60
    axon
    1.59
     Valley
    1.57
     Shah
    1.57
    abad
    1.57
    illac
    1.55
    Activations Density 0.201%

    No Known Activations