© 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. 12600
    Prev
    Next
    INDEX
    Explanations

    references to legal or formal proceedings

    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
    369
    +0.21
    1.2%
    484
    +0.12
    0.7%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.21
    0.11
    484
    +0.12
    0.08
    67
    +0.11
    0.07
    Negative Logits
    ↵
    -1.87
    -1.87
     ↵
    -1.87
              ↵
    -1.87
    č↵
    -1.87
    ↵
    -1.87
    ↵
    -1.87
    ↵
    -1.87
    ↵
    -1.87
    -1.87
    POSITIVE LOGITS
     yourself
    1.42
    ns
    1.36
    nd
    1.34
    pson
    1.32
     outwe
    1.29
     yourselves
    1.28
    odal
    1.27
     differently
    1.26
     pounds
    1.25
    HL
    1.21
    Activations Density 0.687%

    No Known Activations