© 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. 4-RES-SM
    11. 14194
    Prev
    Next
    INDEX
    Explanations

    references to the word "your" 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    156
    +0.25
    1.5%
    497
    +0.11
    0.6%
    410
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.25
    0.05
    145
    +0.11
    0.07
    81
    +0.10
    0.05
    Negative Logits
     thereof
    -2.13
     itself
    -2.01
    emann
    -2.00
    à«ĩ
    -1.82
    OWS
    -1.74
    ία
    -1.70
    esan
    -1.66
    sten
    -1.66
     0000000000000000000000000000000000
    -1.64
    icar
    -1.60
    POSITIVE LOGITS
     own
    3.81
     favorite
    2.71
    self
    2.62
     favourite
    2.50
     liking
    2.22
     partner
    2.16
     choosing
    2.15
     friends
    2.15
     colleagues
    2.09
     yourself
    2.07
    Activations Density 0.460%

    No Known Activations