© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11724
    Prev
    Next
    INDEX
    Explanations

    technical terms and values, particularly related to coding and numerical expressions

    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
    78
    +0.16
    0.9%
    219
    +0.15
    0.9%
    153
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.16
    -0.00
    255
    +0.15
    -0.01
    219
    +0.12
    0.03
    Negative Logits
    .^\[[@
    -1.80
    .[^
    -1.74
    .+
    -1.73
    .*;
    -1.71
    "</
    -1.67
    .</
    -1.65
    .”).
    -1.63
    ./
    -1.62
    .
    -1.55
    .\[
    -1.54
    POSITIVE LOGITS
    obbsee
    1.57
    )](#
    1.49
     she
    1.49
    ))/((-
    1.49
    Women
    1.44
    ))/(
    1.39
     queen
    1.38
     heels
    1.35
    ))/(-
    1.31
     Agreement
    1.30
    Activations Density 0.228%

    No Known Activations