© 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. 1-RES-SM
    11. 24465
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "re-"

    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
    385
    +0.15
    0.9%
    68
    +0.12
    0.7%
    184
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.15
    0.04
    385
    +0.12
    0.03
    184
    +0.11
    0.03
    Negative Logits
     welfare
    -1.69
    chitz
    -1.68
    ODY
    -1.61
    {$
    -1.39
    ).$
    -1.34
    anni
    -1.34
    agnetic
    -1.34
    yy
    -1.33
    onen
    -1.32
    OUR
    -1.31
    POSITIVE LOGITS
    chts
    2.23
    versible
    1.81
    commended
    1.68
    peated
    1.67
    uters
    1.67
    plic
    1.65
    naissance
    1.61
    cept
    1.58
    ceiver
    1.58
    ception
    1.57
    Activations Density 0.107%

    No Known Activations