© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 32173
    Prev
    Next
    INDEX
    Explanations

    references 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
    369
    +0.15
    0.9%
    153
    +0.14
    0.8%
    198
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.15
    0.06
    442
    +0.14
    0.11
    46
    +0.11
    0.02
    Negative Logits
    acular
    -1.41
    onica
    -1.38
    )\].
    -1.37
     morale
    -1.29
    )\]
    -1.29
    uent
    -1.25
    arer
    -1.23
    ench
    -1.23
     MVP
    -1.21
    ven
    -1.20
    POSITIVE LOGITS
    >\
    1.57
     salts
    1.51
    ttes
    1.43
    maid
    1.36
     CIRCUIT
    1.31
    -->
    1.30
    Lemma
    1.27
    cester
    1.26
    kit
    1.25
    strap
    1.24
    Activations Density 4.075%

    No Known Activations