© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 26655
    Prev
    Next
    INDEX
    Explanations

    URLs or references to online content

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    298
    +0.13
    0.7%
    105
    +0.12
    0.7%
    456
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.13
    0.02
    458
    +0.12
    0.02
    425
    +0.11
    0.03
    Negative Logits
     respectively
    -1.97
    ķ
    -1.57
    hta
    -1.50
     etc
    -1.46
    atter
    -1.43
    constraint
    -1.43
    ulic
    -1.43
    -1.42
    ↵↵
    -1.42
    ↵
    -1.42
    POSITIVE LOGITS
     pitches
    1.72
    enix
    1.63
    ruary
    1.48
     mailing
    1.45
    reon
    1.43
    hearing
    1.42
     nods
    1.41
    ozo
    1.41
    FIL
    1.41
    ño
    1.39
    Activations Density 0.204%

    No Known Activations