© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28205
    Prev
    Next
    INDEX
    Explanations

    instances of the word "set" in various contexts

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    376
    +0.13
    0.7%
    53
    +0.11
    0.6%
    490
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.13
    0.04
    53
    +0.11
    0.04
    498
    +0.11
    0.04
    Negative Logits
    idal
    -1.76
    ľ
    -1.60
    ingo
    -1.60
    Ĵ
    -1.59
    clair
    -1.50
    apple
    -1.45
    sburg
    -1.41
    ¡
    -1.36
    UTERS
    -1.35
    ĥ
    -1.33
    POSITIVE LOGITS
    ups
    2.30
    ions
    2.00
     aside
    1.89
     forth
    1.87
    ters
    1.87
    upt
    1.86
     alarms
    1.86
     up
    1.74
     priorities
    1.73
    eness
    1.73
    Activations Density 0.162%

    No Known Activations