© 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. 12762
    Prev
    Next
    INDEX
    Explanations

    mentions of Microsoft-related terms and browser-specific properties

    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
    415
    +0.15
    0.8%
    18
    +0.14
    0.8%
    369
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.15
    0.01
    92
    +0.14
    0.02
    415
    +0.13
    0.01
    Negative Logits
     minors
    -1.75
    EXPORT
    -1.63
    duct
    -1.60
    usion
    -1.55
    gebra
    -1.55
    rent
    -1.53
    ICE
    -1.53
    ishment
    -1.48
    ductive
    -1.46
    dehyde
    -1.45
    POSITIVE LOGITS
    bian
    1.67
    elves
    1.64
    chle
    1.63
    chal
    1.59
    à±į
    1.54
    leys
    1.51
    now
    1.49
    boro
    1.45
    ht
    1.42
     life
    1.42
    Activations Density 0.136%

    No Known Activations