© 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. 10396
    Prev
    Next
    INDEX
    Explanations

    references to various forms of measurements or statistics

    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
    156
    +0.14
    0.8%
    511
    +0.13
    0.8%
    153
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.14
    0.06
    511
    +0.13
    0.12
    73
    +0.12
    0.11
    Negative Logits
    ↵
    -11.69
    -11.69
    ↵  âĢĥ
    -11.69
    <|outofrange|>
    -11.69
    ↵↵
    -11.69
    ↵↵
    -11.69
    <|outofrange|>
    -11.69
    ↵
    -11.69
    <|outofrange|>
    -11.69
      ↵
    -11.69
    POSITIVE LOGITS
    creen
    2.96
    ystems
    2.84
    hip
    2.73
    pace
    2.69
    chool
    2.64
    heet
    2.57
    chitz
    2.56
    hell
    2.50
    ophageal
    2.49
    ystem
    2.47
    Activations Density 1.503%

    No Known Activations