© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26400
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and regulatory 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
    326
    +0.18
    1.0%
    156
    +0.15
    0.8%
    186
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.18
    -0.02
    186
    +0.15
    0.07
    403
    +0.12
    0.07
    Negative Logits
    Ŀ
    -2.09
    ¿
    -2.06
    Ļ
    -1.92
    ¹
    -1.85
    ↵
    -1.84
    ↵↵
    -1.84
    -1.84
    ↵
    -1.84
    <|outofrange|>
    -1.84
    č↵
    -1.84
    POSITIVE LOGITS
    eton
    1.80
    ucid
    1.75
    atche
    1.72
    isman
    1.60
    igent
    1.58
    ert
    1.58
     nowadays
    1.56
    bane
    1.53
    oman
    1.53
    ushima
    1.52
    Activations Density 3.018%

    No Known Activations