© 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. 1-RES-SM
    11. 27446
    Prev
    Next
    INDEX
    Explanations

    numeric values related to legal and financial contexts

    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
    292
    +0.14
    0.8%
    307
    +0.13
    0.8%
    182
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.14
    0.04
    307
    +0.13
    0.04
    292
    +0.13
    0.03
    Negative Logits
    abilities
    -1.54
    rition
    -1.53
     blame
    -1.48
     suspicious
    -1.47
    optera
    -1.44
     World
    -1.44
    oids
    -1.41
    ocracy
    -1.36
     future
    -1.36
    ERIAL
    -1.35
    POSITIVE LOGITS
    uet
    1.89
    uen
    1.74
    00
    1.72
    ian
    1.71
    ĥ½
    1.71
     (§
    1.71
    pal
    1.69
    ĺ
    1.68
    uary
    1.66
     (\~
    1.56
    Activations Density 0.100%

    No Known Activations