© 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. 1-RES-SM
    11. 25692
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    115
    +0.14
    0.8%
    165
    +0.14
    0.8%
    87
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    165
    +0.14
    0.01
    250
    +0.14
    0.02
    87
    +0.13
    0.01
    Negative Logits
    ↵
    -4.68
    -4.68
    ↵↵↵
    -4.68
    ↵
    -4.68
    -4.68
    ↵↵
    -4.68
    ↵
    -4.68
    -4.68
    <|outofrange|>
    -4.68
    <|outofrange|>
    -4.68
    POSITIVE LOGITS
    ween
    1.61
    óg
    1.59
     bipart
    1.56
    ogon
    1.48
     Collaboration
    1.40
    lez
    1.39
    midt
    1.37
    xt
    1.37
    riton
    1.35
     meaning
    1.34
    Activations Density 0.044%

    No Known Activations