© 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. 1-RES-SM
    11. 25086
    Prev
    Next
    INDEX
    Explanations

    the name "Ella" and its variations or derivatives in different 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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.15
    0.9%
    413
    +0.11
    0.6%
    278
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.15
    0.02
    258
    +0.11
    0.02
    40
    +0.11
    0.03
    Negative Logits
    ĵ
    -1.68
    ¿½
    -1.66
     lucky
    -1.63
     equal
    -1.57
    leftarrow
    -1.51
     expensive
    -1.50
     immigrants
    -1.47
     ill
    -1.47
     young
    -1.46
    iates
    -1.45
    POSITIVE LOGITS
    istics
    1.86
    uncher
    1.85
    vine
    1.81
    erie
    1.78
    enstein
    1.68
    issance
    1.65
    zone
    1.63
    endas
    1.56
    ruptcy
    1.54
    quin
    1.53
    Activations Density 0.170%

    No Known Activations