© 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. 27296
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Polina" and its variations

    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
    497
    +0.12
    0.7%
    271
    +0.12
    0.7%
    258
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.00
    258
    +0.12
    0.03
    90
    +0.12
    0.02
    Negative Logits
    Ł
    -2.98
    ĵ
    -2.94
    ¼
    -2.93
    Ģ
    -2.89
    ĺ
    -2.88
    ĥ
    -2.84
    ¥
    -2.83
    ¸
    -2.81
    Ķ
    -2.71
    ĥ½
    -2.70
    POSITIVE LOGITS
     herself
    2.22
    heit
    1.98
    ction
    1.89
     itself
    1.88
    ÈĽ
    1.75
    ustr
    1.66
    ustration
    1.64
    ctions
    1.62
    ises
    1.59
    issance
    1.56
    Activations Density 0.232%

    No Known Activations