© 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. 1-RES-SM
    11. 25531
    Prev
    Next
    INDEX
    Explanations

    phrases indicating notable changes or significant improvements

    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
    376
    +0.12
    0.7%
    350
    +0.12
    0.7%
    23
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    199
    +0.12
    0.02
    78
    +0.12
    0.01
    500
    +0.12
    0.02
    Negative Logits
    ·¸
    -2.34
    ´
    -2.27
    ¼
    -2.00
    -1.95
    ↵
    -1.95
    ↵
    -1.95
    ↵↵
    -1.95
    ↵
    -1.95
    <|outofrange|>
    -1.95
    č↵č↵
    -1.95
    POSITIVE LOGITS
     increased
    1.52
     decreased
    1.46
     coinc
    1.41
     (+
    1.41
     increasing
    1.38
     difference
    1.37
     Hg
    1.37
     span
    1.37
     decreasing
    1.36
     (\~
    1.36
    Activations Density 0.045%

    No Known Activations