© 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. 28932
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and scholarly materials

    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
    +0.21
    1.2%
    144
    +0.13
    0.8%
    365
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.21
    0.07
    184
    +0.13
    0.07
    95
    +0.12
    0.06
    Negative Logits
    §
    -3.58
    ı
    -3.56
     ↵
    -3.46
    -3.46
    ↵
    -3.46
    ↵
    -3.46
    č↵
    -3.46
    ↵
    -3.46
    ↵↵
    -3.46
    ↵↵
    -3.46
    POSITIVE LOGITS
    helf
    3.00
    mith
    2.71
    creen
    2.71
    hip
    2.62
    ystem
    2.60
    erver
    2.53
    ystems
    2.53
    ource
    2.44
    pace
    2.37
    urface
    2.35
    Activations Density 0.666%

    No Known Activations