© 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. 31674
    Prev
    Next
    INDEX
    Explanations

    sections or patterns of text marked by special characters

    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
    410
    +0.19
    1.1%
    450
    +0.14
    0.8%
    205
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.19
    0.03
    163
    +0.14
    0.02
    205
    +0.11
    0.02
    Negative Logits
    )">
    -1.97
    )</
    -1.78
    )."
    -1.70
     stimul
    -1.64
    _."
    -1.62
     donor
    -1.61
    )].
    -1.58
    ).](
    -1.56
     possibility
    -1.51
     counterpart
    -1.46
    POSITIVE LOGITS
    ³
    3.22
    ¦
    3.05
    ²
    3.04
    ¾
    2.94
    Īĺ
    2.94
    ģ
    2.89
    Į
    2.81
    ¬
    2.77
    ĸ
    2.71
    ±
    2.70
    Activations Density 0.106%

    No Known Activations