© 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. 26391
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" indicating context or location

    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
    478
    +0.17
    1.0%
    95
    +0.13
    0.7%
    243
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.17
    0.11
    69
    +0.13
    0.14
    243
    +0.12
    0.14
    Negative Logits
    heads
    -1.58
    iral
    -1.56
    ment
    -1.55
    isters
    -1.51
    head
    -1.45
    pson
    -1.45
    guards
    -1.44
     again
    -1.44
    ings
    -1.43
    amiento
    -1.43
    POSITIVE LOGITS
    ĥ½
    2.93
    »¿
    2.46
              ↵
    2.43
    ↵
    2.43
    ↵
    2.43
    ↵
    2.43
    2.43
    ↵  âĢĥ
    2.43
     ↵
    2.43
    č↵
    2.43
    Activations Density 0.867%

    No Known Activations