© 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 EvalsExportsAPI 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. 26428
    Prev
    Next
    INDEX
    Explanations

    references to Las Vegas

    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
    81
    +0.16
    0.9%
    156
    +0.16
    0.9%
    161
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.16
    0.03
    161
    +0.16
    0.03
    182
    +0.12
    0.02
    Negative Logits
    age
    -1.69
    landers
    -1.64
    irections
    -1.55
    thirds
    -1.54
    estinal
    -1.53
    aster
    -1.50
    elfth
    -1.42
    liest
    -1.42
     colon
    -1.41
    asters
    -1.41
    POSITIVE LOGITS
    vist
    1.82
    CMS
    1.74
    àµį
    1.62
    àµ
    1.62
     analogy
    1.61
    VR
    1.60
    ி
    1.58
    à±į
    1.50
     niche
    1.46
    à´
    1.44
    Activations Density 0.190%

    No Known Activations