© 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. 31357
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures or coding syntax

    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
    43
    +0.12
    0.7%
    21
    +0.11
    0.6%
    53
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.12
    0.06
    43
    +0.11
    0.06
    110
    +0.10
    0.04
    Negative Logits
    ise
    -1.48
    ische
    -1.48
     throughout
    -1.42
     franchise
    -1.40
    blast
    -1.40
    ocur
    -1.38
     compare
    -1.38
    ester
    -1.36
     considering
    -1.36
     ).
    -1.34
    POSITIVE LOGITS
    ©
    3.80
    ĻĤ
    3.67
    ±
    3.62
    ·
    3.52
    °
    3.50
    ¼
    3.50
    Ļª
    3.47
    ¦
    3.47
    ´
    3.45
    ·¸
    3.38
    Activations Density 0.545%

    No Known Activations