© 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. 13399
    Prev
    Next
    INDEX
    Explanations

    references to various organizations, particularly nonprofit and charitable entities

    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
    365
    +0.16
    0.9%
    168
    +0.13
    0.7%
    186
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.16
    0.04
    168
    +0.13
    0.03
    418
    +0.11
    -0.00
    Negative Logits
     aloud
    -1.74
    poons
    -1.59
     tablets
    -1.57
    IJ
    -1.56
     novels
    -1.55
     moi
    -1.51
    pez
    -1.51
    ammar
    -1.50
    gado
    -1.48
     DISTRICT
    -1.47
    POSITIVE LOGITS
     affiliation
    1.95
     affiliations
    1.95
    ically
    1.85
    wide
    1.82
     membership
    1.66
    ally
    1.64
     comprised
    1.62
    member
    1.61
    atics
    1.61
    members
    1.59
    Activations Density 0.283%

    No Known Activations