© 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. 12982
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and data structures

    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
    419
    +0.26
    1.6%
    507
    +0.14
    0.9%
    302
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.26
    0.05
    419
    +0.14
    0.07
    57
    +0.14
    0.08
    Negative Logits
    »¿
    -1.66
    ties
    -1.51
    imester
    -1.51
     increments
    -1.50
     msgid
    -1.35
    ŀ
    -1.32
    ime
    -1.30
     breeze
    -1.27
    ¥
    -1.26
    Ĥ¬
    -1.26
    POSITIVE LOGITS
    ↵³³
    1.60
     behalf
    1.58
    *^
    1.48
    ^âĪĴ/âĪĴ
    1.45
    ablo
    1.42
    onomy
    1.42
     families
    1.41
    ftware
    1.39
     hetero
    1.39
    \]\].
    1.39
    Activations Density 2.440%

    No Known Activations