© 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. 31518
    Prev
    Next
    INDEX
    Explanations

    references to age and gender

    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
    290
    +0.15
    0.9%
    358
    +0.15
    0.9%
    269
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.15
    0.03
    358
    +0.15
    0.03
    51
    +0.10
    0.02
    Negative Logits
     else
    -1.91
     vengeance
    -1.73
    iento
    -1.64
    pton
    -1.59
    ulence
    -1.55
    iente
    -1.52
    >'
    -1.47
    sburg
    -1.45
    ¿½
    -1.43
    uscular
    -1.41
    POSITIVE LOGITS
     adjustment
    1.62
     (±
    1.56
    way
    1.50
    itudinal
    1.50
    frame
    1.50
     cutoff
    1.49
    CTS
    1.48
     cohorts
    1.47
     varying
    1.46
     age
    1.46
    Activations Density 0.099%

    No Known Activations