© 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. 25318
    Prev
    Next
    INDEX
    Explanations

    instances of ellipses or truncated phrases

    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
    478
    +0.19
    1.1%
    23
    +0.13
    0.7%
    258
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.19
    0.13
    279
    +0.13
    0.10
    256
    +0.13
    0.10
    Negative Logits
    tees
    -1.84
    ellar
    -1.80
    uchy
    -1.68
    fficients
    -1.65
     variables
    -1.61
    ificates
    -1.57
    uity
    -1.57
     bets
    -1.57
    culus
    -1.57
     notation
    -1.54
    POSITIVE LOGITS
     Continue
    1.81
    ¸
    1.66
    more
    1.61
    unnumbered
    1.55
    very
    1.52
     </
    1.51
    something
    1.49
    Continue
    1.49
    athed
    1.48
    ı
    1.46
    Activations Density 0.990%

    No Known Activations