© 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. 26294
    Prev
    Next
    INDEX
    Explanations

    items related to community infrastructure and public services

    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
    +0.20
    1.2%
    56
    +0.16
    0.9%
    293
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.20
    0.12
    365
    +0.16
    0.11
    425
    +0.15
    0.12
    Negative Logits
    ĥ½
    -3.41
    §
    -3.23
    ı
    -3.19
    -3.12
    č↵
    -3.12
     ↵
    -3.12
    č↵
    -3.12
    ↵
    -3.12
    -3.12
    č↵
    -3.12
    POSITIVE LOGITS
    creen
    2.46
    mith
    2.29
    ource
    2.22
    ystems
    2.21
    orbent
    2.19
    pace
    2.08
    ystem
    2.03
    cript
    2.00
    heet
    1.99
    hell
    1.94
    Activations Density 2.156%

    No Known Activations