© 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. 10889
    Prev
    Next
    INDEX
    Explanations

    support-related terms or phrases

    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
    183
    +0.13
    0.7%
    350
    +0.13
    0.7%
    34
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.13
    0.01
    350
    +0.13
    0.02
    452
    +0.12
    0.01
    Negative Logits
     awk
    -1.39
     squir
    -1.36
    ophone
    -1.35
    oop
    -1.34
     whale
    -1.33
     cens
    -1.29
     colony
    -1.29
    angling
    -1.29
     PST
    -1.27
    trim
    -1.26
    POSITIVE LOGITS
    ī
    1.92
    Ł
    1.88
    ¾
    1.74
    Ļ
    1.69
    ļ
    1.67
    ª
    1.62
    ¨
    1.61
    ł
    1.58
    Ĩ
    1.58
    ements
    1.56
    Activations Density 0.062%

    No Known Activations