© 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. 2-RES-SM
    11. 13357
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related content

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    110
    +0.17
    1.0%
    478
    +0.15
    0.8%
    410
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.17
    0.04
    424
    +0.15
    0.03
    303
    +0.15
    0.04
    Negative Logits
    ”).
    -1.54
     World
    -1.53
    ி
    -1.49
    )">
    -1.49
    ”),
    -1.47
    ivity
    -1.45
    ↵  ³³³
    -1.45
    <|outofrange|>
    -1.45
    -1.45
     ↵
    -1.45
    POSITIVE LOGITS
    lor
    1.43
     associate
    1.42
     Stark
    1.39
    ull
    1.36
     trump
    1.35
     dou
    1.33
    iana
    1.31
    oka
    1.27
     mind
    1.26
    quette
    1.25
    Activations Density 0.056%

    No Known Activations