© 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. 13054
    Prev
    Next
    INDEX
    Explanations

    words related to programming configurations and parameters

    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
    178
    +0.14
    0.8%
    17
    +0.13
    0.7%
    260
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.14
    0.02
    73
    +0.13
    0.06
    260
    +0.12
    0.06
    Negative Logits
     preponderance
    -2.21
     majority
    -2.02
    tails
    -1.92
    ©
    -1.91
    ¯
    -1.91
    ı
    -1.74
    Ł
    -1.68
    ishes
    -1.68
    pling
    -1.68
    ķ
    -1.67
    POSITIVE LOGITS
    pace
    3.55
    ystem
    3.28
    ource
    3.25
    heet
    3.21
    helf
    3.02
    mith
    2.89
    urface
    2.76
    ymbol
    2.76
    creen
    2.75
    aurus
    2.73
    Activations Density 1.227%

    No Known Activations