© 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. 28710
    Prev
    Next
    INDEX
    Explanations

    terms related to biological or physiological processes that involve induction

    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
    156
    +0.16
    0.9%
    317
    +0.13
    0.8%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.16
    0.01
    148
    +0.13
    0.01
    192
    +0.12
    0.01
    Negative Logits
    clud
    -1.54
    ciparum
    -1.53
     banc
    -1.53
     liter
    -1.50
    bers
    -1.43
    son
    -1.42
     sizeof
    -1.41
     lado
    -1.41
    bered
    -1.39
    sizeof
    -1.38
    POSITIVE LOGITS
     events
    1.53
    itivity
    1.51
     event
    1.42
     injury
    1.40
     pause
    1.37
     plur
    1.36
    ogenicity
    1.35
     activity
    1.35
    Ĵ
    1.33
    Ł
    1.32
    Activations Density 0.052%

    No Known Activations