© 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. 29345
    Prev
    Next
    INDEX
    Explanations

    words indicating quantity or reference in relation to objects or persons

    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
    +0.17
    1.0%
    228
    +0.15
    0.9%
    478
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    228
    +0.17
    0.03
    8
    +0.15
    0.02
    501
    +0.14
    0.02
    Negative Logits
    aire
    -1.75
    naire
    -1.57
    û
    -1.57
    otype
    -1.49
    aires
    -1.48
     performed
    -1.43
    bie
    -1.42
    ants
    -1.42
    stones
    -1.41
    ingo
    -1.38
    POSITIVE LOGITS
    ķ
    4.04
    »¿
    3.97
    ĥ
    3.86
    ľĵ
    3.76
    Į
    3.75
    ¿½
    3.73
    ·¸
    3.72
    ³
    3.66
    ĸ
    3.64
               ↵
    3.61
    Activations Density 0.160%

    No Known Activations