© 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. 4-RES-SM
    11. 10961
    Prev
    Next
    INDEX
    Explanations

    references to customer service and customer relations

    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
    492
    +0.13
    0.7%
    241
    +0.13
    0.7%
    348
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    45
    +0.13
    0.03
    492
    +0.13
    0.04
    418
    +0.12
    0.02
    Negative Logits
    er
    -1.76
    ause
    -1.64
    osaurs
    -1.52
    ="../../../../../../
    -1.50
    ensis
    -1.49
    ers
    -1.48
    anoi
    -1.47
    bj
    -1.47
    STEM
    -1.45
    structor
    -1.43
    POSITIVE LOGITS
     satisfaction
    2.52
     alike
    2.08
     experience
    2.07
     loyalty
    2.04
     reviews
    1.95
     expectations
    1.94
    ele
    1.94
     feedback
    1.91
     desires
    1.87
     desire
    1.86
    Activations Density 0.516%

    No Known Activations