© 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. 27318
    Prev
    Next
    INDEX
    Explanations

    numerical data and specific references to events or operations

    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
    36
    +0.12
    0.7%
    271
    +0.12
    0.7%
    331
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.12
    0.16
    506
    +0.12
    0.09
    440
    +0.12
    0.07
    Negative Logits
     INTRODUCTION
    -1.54
    :**
    -1.47
    ↵³³
    -1.45
    icular
    -1.42
    iella
    -1.38
     colleagues
    -1.35
     alternative
    -1.35
     analogy
    -1.30
    ue
    -1.29
     alternatives
    -1.29
    POSITIVE LOGITS
    deal
    1.73
     hers
    1.58
    ships
    1.48
    asts
    1.48
    ever
    1.48
    ogr
    1.48
    antly
    1.45
    psy
    1.44
    cludes
    1.38
    ugh
    1.38
    Activations Density 4.196%

    No Known Activations