© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 32520
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the frequency of occurrences or intervals of timing

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    195
    +0.12
    0.7%
    436
    +0.12
    0.7%
    357
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.12
    0.06
    195
    +0.12
    0.05
    182
    +0.11
    0.06
    Negative Logits
    ¦
    -1.64
    amar
    -1.56
     chief
    -1.42
    /*
    -1.40
     ↵↵
    -1.38
    VD
    -1.37
    ivities
    -1.33
     measures
    -1.32
     whereby
    -1.32
     directly
    -1.31
    POSITIVE LOGITS
     hep
    1.83
     chance
    1.53
     convenience
    1.49
     desperation
    1.49
     nature
    1.48
     success
    1.47
    hearted
    1.43
    tered
    1.42
    tons
    1.41
    sidered
    1.38
    Activations Density 0.952%

    No Known Activations