© 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. 32161
    Prev
    Next
    INDEX
    Explanations

    closing parentheses 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
    258
    +0.14
    0.8%
    208
    +0.12
    0.7%
    263
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.14
    0.06
    128
    +0.12
    0.04
    162
    +0.12
    0.05
    Negative Logits
    °
    -5.51
    ħ
    -5.40
    Īĺ
    -5.18
    -5.16
    ↵↵↵
    -5.16
       ↵
    -5.16
    ↵
    -5.16
    -5.16
    č↵č↵
    -5.16
    ↵
    -5.16
    POSITIVE LOGITS
    circum
    1.51
    skirts
    1.49
    .")
    1.42
    ivalent
    1.41
    imester
    1.41
    mar
    1.40
    umbent
    1.39
    »,
    1.38
    bil
    1.37
    tur
    1.36
    Activations Density 0.202%

    No Known Activations