© 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. 13520
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer service and support

    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
    348
    +0.15
    0.8%
    21
    +0.13
    0.7%
    288
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.15
    0.08
    288
    +0.13
    0.08
    251
    +0.12
    0.07
    Negative Logits
    emic
    -1.52
    Ļª
    -1.43
    ibi
    -1.39
    thal
    -1.38
    ches
    -1.38
    phal
    -1.37
    ides
    -1.35
    chem
    -1.35
    tails
    -1.32
    htra
    -1.31
    POSITIVE LOGITS
     spam
    2.07
     email
    2.04
     disclaim
    1.86
     confidentiality
    1.84
     cookies
    1.79
     privacy
    1.76
     Privacy
    1.75
     password
    1.73
     copyright
    1.72
     anonym
    1.68
    Activations Density 0.822%

    No Known Activations