© 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. 14117
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be"

    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
    23
    +0.28
    1.6%
    142
    +0.12
    0.7%
    105
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.28
    0.16
    356
    +0.12
    0.10
    247
    +0.12
    0.11
    Negative Logits
    ł
    -4.45
    Į
    -4.36
    -4.24
    ↵
    -4.24
    <|outofrange|>
    -4.24
    -4.24
    č↵
    -4.24
           ↵
    -4.24
    -4.24
    -4.24
    POSITIVE LOGITS
    rael
    1.95
    omerase
    1.80
     always
    1.67
     replaced
    1.64
    ?’
    1.61
     impaired
    1.60
     mute
    1.59
     gone
    1.58
     unable
    1.58
    ?'
    1.58
    Activations Density 1.134%

    No Known Activations