© 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. 27796
    Prev
    Next
    INDEX
    Explanations

    numerical values or references to data types

    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
    478
    +0.13
    0.7%
    165
    +0.13
    0.7%
    87
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    165
    +0.13
    0.03
    202
    +0.13
    0.03
    463
    +0.12
    0.02
    Negative Logits
    uximab
    -1.85
    àµį
    -1.72
    alities
    -1.69
    etry
    -1.61
    unov
    -1.61
    ts
    -1.56
    eln
    -1.52
    cz
    -1.52
    zes
    -1.47
    isson
    -1.45
    POSITIVE LOGITS
    ·
    2.22
    ¿½
    2.09
    ·¸
    1.98
    ¼
    1.68
    ĸ´
    1.63
    ¸
    1.62
    Ŀ
    1.61
    ½
    1.57
    ¹
    1.53
    ī
    1.52
    Activations Density 0.037%

    No Known Activations