© 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. 24603
    Prev
    Next
    INDEX
    Explanations

    entities related to healthcare and environmental organizations

    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
    156
    +0.18
    1.0%
    83
    +0.15
    0.9%
    271
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.18
    0.02
    83
    +0.15
    0.08
    34
    +0.13
    0.09
    Negative Logits
     lovers
    -1.83
     lover
    -1.71
     Kindle
    -1.64
     nature
    -1.61
     guessed
    -1.52
     unfamiliar
    -1.51
     yourself
    -1.50
     patience
    -1.45
     cons
    -1.42
     conjugation
    -1.40
    POSITIVE LOGITS
    illery
    1.66
    eras
    1.61
    úblic
    1.56
    apon
    1.50
    orts
    1.50
    ield
    1.47
    aternal
    1.46
    istory
    1.45
    ubern
    1.43
    liance
    1.43
    Activations Density 0.725%

    No Known Activations