© 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. 27589
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people and places

    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
    369
    +0.21
    1.2%
    410
    +0.15
    0.9%
    161
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.21
    0.16
    369
    +0.15
    0.07
    59
    +0.12
    0.09
    Negative Logits
    osition
    -1.89
    oretic
    -1.77
    osing
    -1.75
    iction
    -1.70
    oming
    -1.66
    xico
    -1.60
    ylate
    -1.58
    ESULT
    -1.56
    urope
    -1.51
    ledge
    -1.48
    POSITIVE LOGITS
    ¿
    2.86
    ī
    2.85
    ĻĤ
    2.85
    ·
    2.82
    «
    2.79
    ¦
    2.77
    ©
    2.72
    ij
    2.69
    ½
    2.69
    µ
    2.64
    Activations Density 0.944%

    No Known Activations