© 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. 2-RES-SM
    11. 31128
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical comparisons and calculations, specifically focusing on common denominators, multiples, and ordering of numbers

    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
    347
    +0.13
    0.7%
    315
    +0.12
    0.7%
    4
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.13
    0.01
    131
    +0.12
    0.02
    67
    +0.12
    0.01
    Negative Logits
    sed
    -1.59
    pshire
    -1.55
    Č
    -1.48
    ()</
    -1.46
    ...](
    -1.45
    issions
    -1.42
    ms
    -1.39
    orect
    -1.39
    mine
    -1.37
    ocracy
    -1.36
    POSITIVE LOGITS
     Factor
    1.62
    innati
    1.44
     factor
    1.41
    encial
    1.40
    "}](#
    1.35
     (,
    1.35
    ème
    1.34
    ellt
    1.33
     discloses
    1.30
     Draft
    1.30
    Activations Density 0.071%

    No Known Activations