© 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. 29791
    Prev
    Next
    INDEX
    Explanations

    topics related to user interaction and experience

    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
    450
    +0.15
    0.8%
    282
    +0.13
    0.7%
    407
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.15
    0.06
    17
    +0.13
    0.01
    242
    +0.12
    0.04
    Negative Logits
     upstream
    -1.50
    acket
    -1.48
    ayette
    -1.47
    head
    -1.47
     BGCOLOR
    -1.45
    strong
    -1.45
    ech
    -1.44
    woods
    -1.42
    jest
    -1.41
     onward
    -1.41
    POSITIVE LOGITS
     personas
    1.57
    istration
    1.56
     credentials
    1.52
     wait
    1.49
    inees
    1.47
     assigns
    1.45
     premises
    1.43
     reference
    1.41
    isation
    1.38
    ĭ
    1.36
    Activations Density 0.807%

    No Known Activations