© 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. 29120
    Prev
    Next
    INDEX
    Explanations

    criteria and qualifications for applicants in a recruitment context

    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
    23
    +0.22
    1.2%
    156
    +0.18
    1.0%
    17
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.22
    0.14
    423
    +0.18
    0.06
    240
    +0.15
    -0.04
    Negative Logits
    istory
    -1.71
    inspired
    -1.66
     ways
    -1.61
     way
    -1.60
     thinkers
    -1.54
     puzzles
    -1.50
     insights
    -1.49
    watson
    -1.47
     storytelling
    -1.46
    wald
    -1.46
    POSITIVE LOGITS
    ĻĤ
    3.88
    »¿
    3.13
    ľĵ
    3.08
    ī
    2.99
    ³
    2.97
    »
    2.96
    Ļª
    2.92
      ↵
    2.90
    č↵č↵
    2.89
    2.89
    Activations Density 3.480%

    No Known Activations