© 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. 2-RES-SM
    11. 27258
    Prev
    Next
    INDEX
    Explanations

    instances of friendliness and positive interactions in service-related 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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    394
    +0.13
    0.7%
    232
    +0.11
    0.6%
    466
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.13
    0.05
    394
    +0.11
    0.06
    232
    +0.11
    0.06
    Negative Logits
    urop
    -1.65
    urin
    -1.50
     photography
    -1.48
     programmed
    -1.43
    asmod
    -1.42
    :&
    -1.42
    boarding
    -1.42
     viability
    -1.40
     fatal
    -1.39
    atal
    -1.38
    POSITIVE LOGITS
    liness
    1.96
    ness
    1.89
    swers
    1.80
    paces
    1.71
    mouth
    1.69
    ---|---
    1.68
    ity
    1.56
     reminder
    1.56
    est
    1.55
    {}{
    1.52
    Activations Density 0.608%

    No Known Activations