© 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. 28477
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions, exceptions, or qualifications in statements

    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
    23
    +0.18
    1.0%
    75
    +0.12
    0.7%
    420
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.18
    0.06
    420
    +0.12
    0.04
    23
    +0.11
    0.08
    Negative Logits
    inery
    -1.64
    nier
    -1.62
    ensable
    -1.50
    nÄĽ
    -1.45
    :`
    -1.44
    estock
    -1.40
    uce
    -1.39
    iner
    -1.35
    ensis
    -1.32
    arium
    -1.31
    POSITIVE LOGITS
    ¿½
    2.11
    ·¸
    1.63
    ¥
    1.56
     divorced
    1.45
    +}
    1.42
    ī
    1.40
     minor
    1.39
     due
    1.38
    then
    1.38
     did
    1.36
    Activations Density 1.187%

    No Known Activations