© 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. 27130
    Prev
    Next
    INDEX
    Explanations

    text that discusses standardized practices and measures, often in research or report contexts

    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
    400
    +0.17
    0.9%
    171
    +0.12
    0.7%
    206
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    400
    +0.17
    0.04
    171
    +0.12
    0.04
    206
    +0.11
    0.03
    Negative Logits
    ĭ
    -3.13
    Īĺ
    -2.65
    Ļª
    -2.56
    ·¸
    -2.33
    Ĥ
    -2.31
    ±
    -2.30
    ĨĴ
    -2.26
    ¸
    -2.23
    Ĩ
    -2.17
    ľĵ
    -2.15
    POSITIVE LOGITS
     includes
    1.93
     contains
    1.80
     belongs
    1.79
     lies
    1.57
     consists
    1.54
     comes
    1.54
     incorporates
    1.51
     develops
    1.50
     applies
    1.46
     relies
    1.45
    Activations Density 0.882%

    No Known Activations