© 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. 12744
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and file formats

    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
    +0.33
    2.0%
    21
    +0.19
    1.2%
    356
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.33
    0.11
    21
    +0.19
    -0.00
    464
    +0.14
    -0.01
    Negative Logits
    ī
    -2.28
    ©
    -2.28
    -2.27
    ↵
    -2.27
    ↵
    -2.27
    ↵
    -2.27
    ↵↵
    -2.27
    <|outofrange|>
    -2.27
    -2.27
    ↵↵
    -2.27
    POSITIVE LOGITS
     puzzle
    1.56
     treasure
    1.51
     methamphetamine
    1.46
     inheritance
    1.42
     mystery
    1.41
    blockList
    1.41
     creature
    1.39
     amyl
    1.39
    iella
    1.39
     rice
    1.38
    Activations Density 2.410%

    No Known Activations