© 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. 26640
    Prev
    Next
    INDEX
    Explanations

    URLs or references related to GitHub repositories and licenses

    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
    74
    +0.12
    0.7%
    499
    +0.11
    0.7%
    59
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.12
    0.04
    329
    +0.11
    0.03
    463
    +0.10
    0.03
    Negative Logits
    Į
    -1.90
    Ĺ
    -1.88
    Ń
    -1.85
    Ģ
    -1.83
    »¿
    -1.81
    ĺ
    -1.74
    .'"
    -1.73
    ½
    -1.71
    Ħ
    -1.65
    Ĭ
    -1.62
    POSITIVE LOGITS
     publisher
    1.68
     Else
    1.53
     DISCLAIM
    1.52
     waiver
    1.51
     arXiv
    1.48
     PubMed
    1.48
    ppat
    1.45
     compliant
    1.40
     publicly
    1.38
     Redistributions
    1.36
    Activations Density 0.443%

    No Known Activations