© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 29397
    Prev
    Next
    INDEX
    Explanations

    instances of the word "different."

    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%
    457
    +0.14
    0.8%
    29
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.18
    0.05
    392
    +0.14
    0.04
    29
    +0.13
    0.03
    Negative Logits
    ycin
    -1.72
    fter
    -1.55
    CHA
    -1.51
    bers
    -1.50
    =====
    -1.50
     WARRANTY
    -1.43
    kan
    -1.40
    ken
    -1.40
    ===
    -1.40
    belt
    -1.38
    POSITIVE LOGITS
     kinds
    2.19
     sized
    2.17
     sexes
    2.17
     coloured
    2.10
    iates
    2.04
    iator
    2.00
     sizes
    2.00
    ities
    1.97
    ials
    1.96
     sorts
    1.90
    Activations Density 0.065%

    No Known Activations