© 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. 1-RES-SM
    11. 24144
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ro," which may indicate a focus on specific terminology or colloquial expressions related to "roaming" or similar concepts

    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
    410
    +0.14
    0.8%
    59
    +0.14
    0.8%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.14
    0.02
    185
    +0.14
    0.02
    468
    +0.12
    0.01
    Negative Logits
     continuity
    -1.71
    CDATA
    -1.55
    olate
    -1.48
     unity
    -1.47
     resemblance
    -1.44
    oglobin
    -1.44
     future
    -1.43
    olation
    -1.43
    ystem
    -1.40
     disguise
    -1.38
    POSITIVE LOGITS
    ½
    3.78
    Ģ
    3.61
    ¸
    3.61
    ¾
    3.55
    Ĵ
    3.49
    ł
    3.47
    ĺ
    3.43
    ·
    3.40
    ±
    3.39
    ¥
    3.37
    Activations Density 0.054%

    No Known Activations