© 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. 28420
    Prev
    Next
    INDEX
    Explanations

    instances of the word "example"

    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
    365
    +0.15
    0.8%
    23
    +0.11
    0.6%
    345
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.15
    0.03
    345
    +0.11
    0.03
    353
    +0.11
    0.03
    Negative Logits
    ?**
    -1.60
    "?
    -1.58
    .**
    -1.49
    ._
    -1.48
     jointly
    -1.43
    _."
    -1.43
    .
    -1.42
     themselves
    -1.42
    _.
    -1.40
     defend
    -1.40
    POSITIVE LOGITS
    mered
    1.69
    apter
    1.62
    oelectric
    1.61
    orphic
    1.55
    let
    1.52
    anmar
    1.44
    liness
    1.42
    come
    1.41
    terest
    1.39
    vasive
    1.39
    Activations Density 0.056%

    No Known Activations