© 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. 26385
    Prev
    Next
    INDEX
    Explanations

    expressions related to acknowledgment and personal reflection

    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
    263
    +0.24
    1.4%
    489
    +0.15
    0.9%
    185
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.24
    0.16
    323
    +0.15
    0.07
    301
    +0.12
    0.07
    Negative Logits
    ĻĤ
    -4.94
    ¿
    -4.52
    ħ
    -4.52
    ľ
    -4.49
    Ļª
    -4.46
    ľĵ
    -4.42
    ŀ
    -4.42
    ½
    -4.38
    ĥ
    -4.38
    ļ
    -4.36
    POSITIVE LOGITS
    edly
    2.03
    lement
    1.50
     summar
    1.47
     congrat
    1.46
    tell
    1.45
    talk
    1.43
    enge
    1.43
     ÑĩÑĤо
    1.42
     sorry
    1.42
    itious
    1.40
    Activations Density 1.812%

    No Known Activations