© 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. 11357
    Prev
    Next
    INDEX
    Explanations

    references to technological terms and jargon

    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
    +0.42
    2.8%
    307
    +0.15
    1.0%
    172
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    510
    +0.42
    0.19
    25
    +0.15
    0.18
    274
    +0.14
    0.17
    Negative Logits
    Ļª
    -5.50
     ↵
    -5.40
    ↵↵
    -5.40
    -5.40
    <|outofrange|>
    -5.40
    ↵↵↵
    -5.40
    <|outofrange|>
    -5.40
    <|outofrange|>
    -5.40
    ↵↵
    -5.40
    ↵
    -5.40
    POSITIVE LOGITS
    lining
    1.33
    anium
    1.29
     ANN
    1.27
    verting
    1.21
    then
    1.18
     Chr
    1.18
    anmar
    1.16
    hematic
    1.12
     notch
    1.12
    .:
    1.10
    Activations Density 4.879%

    No Known Activations