© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 12495
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the letter 'g'

    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
    397
    +0.18
    1.0%
    369
    +0.17
    1.0%
    412
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    215
    +0.18
    0.05
    485
    +0.17
    0.03
    369
    +0.16
    0.02
    Negative Logits
    tro
    -1.52
     time
    -1.51
     moment
    -1.50
    TRODUCTION
    -1.49
    inus
    -1.47
    ecl
    -1.47
    correct
    -1.38
     knots
    -1.38
    ances
    -1.36
     urgent
    -1.36
    POSITIVE LOGITS
    aussian
    1.91
    rosse
    1.65
    hetto
    1.64
    RPC
    1.63
    nut
    1.61
    ulf
    1.60
    hetti
    1.57
    ulates
    1.56
    athering
    1.56
    olds
    1.55
    Activations Density 0.105%

    No Known Activations