© 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. 4-RES-SM
    11. 11064
    Prev
    Next
    INDEX
    Explanations

    references to various types of content and 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/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
    466
    +0.23
    1.4%
    25
    +0.18
    1.1%
    357
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.23
    0.09
    34
    +0.18
    0.08
    494
    +0.14
    0.01
    Negative Logits
    ""
    -1.71
    »¿
    -1.69
    :`
    -1.63
    ¾
    -1.59
    []{
    -1.55
    .'"
    -1.55
    £
    -1.53
    ij
    -1.51
    .’”
    -1.51
    ©
    -1.50
    POSITIVE LOGITS
     others
    2.08
     Exchange
    2.04
     Commerce
    1.96
     other
    1.83
     Access
    1.83
     Other
    1.82
     Sons
    1.82
     Explorer
    1.82
     Monitor
    1.81
     Control
    1.81
    Activations Density 0.729%

    No Known Activations