© 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. 12695
    Prev
    Next
    INDEX
    Explanations

    references to people and their relationships

    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
    21
    +0.24
    1.4%
    156
    +0.13
    0.8%
    422
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.24
    0.08
    320
    +0.13
    0.07
    441
    +0.13
    -0.01
    Negative Logits
    Ļª
    -2.51
    Ŀ
    -2.45
    ľĵ
    -2.43
     ↵
    -2.37
    -2.37
    <|outofrange|>
    -2.37
    <|outofrange|>
    -2.37
          ↵
    -2.37
       ↵
    -2.37
    <|outofrange|>
    -2.37
    POSITIVE LOGITS
     allegedly
    1.69
     resided
    1.59
    stood
    1.57
     reside
    1.48
     resides
    1.46
    rest
    1.46
     originated
    1.46
     congreg
    1.45
     freely
    1.41
    held
    1.40
    Activations Density 0.963%

    No Known Activations