© 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. 12808
    Prev
    Next
    INDEX
    Explanations

    references to the GNU General Public License

    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
    111
    +0.14
    0.8%
    74
    +0.12
    0.7%
    431
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.14
    0.02
    431
    +0.12
    0.02
    456
    +0.12
    0.02
    Negative Logits
    ı
    -1.78
    ¯
    -1.65
    ľĵ
    -1.63
     dating
    -1.51
    akia
    -1.49
    urin
    -1.40
    Ł
    -1.39
     likely
    -1.39
     proportions
    -1.34
    hing
    -1.33
    POSITIVE LOGITS
     Opinion
    1.59
     GPL
    1.54
    genstein
    1.48
    missive
    1.48
     letter
    1.46
     GENER
    1.43
    bery
    1.39
    bsd
    1.39
     General
    1.37
     harmless
    1.36
    Activations Density 0.042%

    No Known Activations