© 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. 12975
    Prev
    Next
    INDEX
    Explanations

    inquiries about interest or involvement in various topics or activities

    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
    372
    +0.15
    0.8%
    450
    +0.11
    0.6%
    258
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.15
    0.04
    450
    +0.11
    0.04
    119
    +0.11
    0.03
    Negative Logits
    ĥ½
    -3.03
    ĻĤ
    -2.54
    Īĺ
    -2.53
    ľĵ
    -2.53
     ↵
    -2.51
    ↵
    -2.51
    ↵
    -2.51
    ↵
    -2.51
    ↵
    -2.51
              ↵
    -2.51
    POSITIVE LOGITS
    ness
    2.01
    hold
    1.61
    nier
    1.59
    teen
    1.56
    ly
    1.54
    liness
    1.53
    lé
    1.53
    lier
    1.50
     groups
    1.50
    lement
    1.49
    Activations Density 0.349%

    No Known Activations