© 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. 1-RES-SM
    6. 27307
    Prev
    Next
    INDEX
    Explanations

    dates and names associated with individuals

    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
    315
    +0.12
    0.7%
    266
    +0.12
    0.6%
    271
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.12
    0.02
    388
    +0.12
    0.02
    62
    +0.12
    0.01
    Negative Logits
    paste
    -1.66
     rect
    -1.62
    flies
    -1.58
    cyst
    -1.56
    ires
    -1.54
    exposure
    -1.52
    actual
    -1.50
    ittings
    -1.50
     precautions
    -1.48
     precaution
    -1.47
    POSITIVE LOGITS
     unhappy
    1.48
     feud
    1.47
     autosomal
    1.43
    nant
    1.43
     divorced
    1.40
     Confed
    1.40
     unconscious
    1.40
     disrupted
    1.38
     silent
    1.37
    ivel
    1.36
    Activations Density 0.116%

    No Known Activations