© 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. 1-RES-SM
    11. 29188
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership or relationships

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    478
    +0.13
    0.7%
    81
    +0.12
    0.7%
    264
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.13
    0.09
    264
    +0.12
    0.08
    505
    +0.12
    0.06
    Negative Logits
    osa
    -1.69
    (){
    -1.62
     unto
    -1.53
    "}](#
    -1.50
    imus
    -1.49
    oso
    -1.49
    ferent
    -1.46
    etus
    -1.40
    ale
    -1.37
     extends
    -1.36
    POSITIVE LOGITS
     lifetime
    1.74
    Decided
    1.63
     birthday
    1.47
    Submitted
    1.45
     greatest
    1.38
    ethical
    1.38
     been
    1.36
     Always
    1.35
    ittest
    1.34
     Got
    1.33
    Activations Density 0.413%

    No Known Activations