© 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. 14052
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "been" in various contexts

    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
    +0.16
    0.9%
    319
    +0.13
    0.7%
    276
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    65
    +0.16
    0.07
    336
    +0.13
    0.07
    319
    +0.12
    0.05
    Negative Logits
    ī
    -5.08
    £
    -4.95
    İ
    -4.93
    ĩ
    -4.79
    ģ
    -4.79
    ĭ
    -4.73
    Ī
    -4.72
    ł
    -4.71
    §
    -4.66
    Ħ
    -4.55
    POSITIVE LOGITS
     unsuccessful
    1.81
    een
    1.74
     extensively
    1.63
    agland
    1.59
     inactive
    1.57
     successful
    1.51
     unsuccess
    1.51
     okay
    1.49
    emente
    1.41
     faithfully
    1.40
    Activations Density 0.174%

    No Known Activations