© 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. 31806
    Prev
    Next
    INDEX
    Explanations

    instances of the word "got"

    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
    376
    +0.15
    0.9%
    53
    +0.15
    0.9%
    478
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.15
    0.04
    287
    +0.15
    0.04
    358
    +0.10
    0.03
    Negative Logits
    unc
    -1.73
    ¦
    -1.70
    disambiguation
    -1.69
    ivid
    -1.63
    ©
    -1.60
    §
    -1.58
    ¨
    -1.56
    ¡
    -1.54
    Ĵ
    -1.52
    ŀ
    -1.49
    POSITIVE LOGITS
     pains
    2.06
     rid
    1.93
    gie
    1.65
     problems
    1.63
     trouble
    1.63
     stuck
    1.63
     ket
    1.56
     legs
    1.54
     priority
    1.51
     tired
    1.50
    Activations Density 0.134%

    No Known Activations