© 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. 24864
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pass."

    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
    148
    +0.12
    0.7%
    376
    +0.11
    0.6%
    152
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    473
    +0.12
    0.02
    120
    +0.11
    0.02
    114
    +0.11
    0.02
    Negative Logits
    woke
    -2.07
    keit
    -1.53
    een
    -1.52
     Arts
    -1.51
    ---|---
    -1.40
    apolis
    -1.38
    eLife
    -1.37
    oarthritis
    -1.37
    istic
    -1.37
    anan
    -1.34
    POSITIVE LOGITS
    wd
    1.97
    ports
    1.64
    enger
    1.56
    ulous
    1.52
    engers
    1.50
     holders
    1.49
    phrase
    1.48
    airs
    1.47
    ittings
    1.46
    ibles
    1.46
    Activations Density 0.052%

    No Known Activations