© 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. 31232
    Prev
    Next
    INDEX
    Explanations

    references to "other" in various 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
    97
    +0.12
    0.7%
    306
    +0.11
    0.6%
    402
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.12
    0.03
    306
    +0.11
    0.03
    97
    +0.11
    0.03
    Negative Logits
    apine
    -1.72
    arde
    -1.57
    ibaba
    -1.55
    $^{-
    -1.54
    illon
    -1.43
    oqu
    -1.43
    ennial
    -1.40
    @{
    -1.37
    umab
    -1.35
     any
    -1.33
    POSITIVE LOGITS
    world
    2.14
     thread
    1.81
     side
    1.80
     half
    1.60
     threads
    1.59
    bie
    1.58
     kinds
    1.57
     sides
    1.55
     aspects
    1.47
    where
    1.44
    Activations Density 0.113%

    No Known Activations