© 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. 4-RES-SM
    11. 13636
    Prev
    Next
    INDEX
    Explanations

    references to databases and their related concepts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    357
    +0.19
    1.1%
    141
    +0.12
    0.7%
    422
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.19
    0.03
    189
    +0.12
    0.03
    440
    +0.10
    0.01
    Negative Logits
    ij
    -4.85
    ĵ
    -4.72
    ³
    -4.70
    §
    -4.69
    ĨĴ
    -4.66
    ½
    -4.53
    Ļª
    -4.45
    Ĵ
    -4.40
    ¿
    -4.32
    Ļ
    -4.24
    POSITIVE LOGITS
     schema
    2.21
     server
    2.15
     database
    2.04
     db
    1.95
     backend
    1.89
     queries
    1.88
     servers
    1.88
     entries
    1.86
     owner
    1.84
     reader
    1.82
    Activations Density 0.137%

    No Known Activations