© 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. 14313
    Prev
    Next
    INDEX
    Explanations

    structured formats and data within the text

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.15
    0.9%
    98
    +0.14
    0.8%
    507
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.20
    111
    +0.14
    0.16
    156
    +0.13
    0.20
    Negative Logits
    ±
    -1.99
    ]_
    -1.83
    §
    -1.81
    Ħ
    -1.68
    ª
    -1.68
    Ļ
    -1.65
    ij
    -1.57
     labels
    -1.57
    ¿
    -1.56
    ©
    -1.54
    POSITIVE LOGITS
    opter
    1.68
    rá
    1.50
    EXPORT
    1.48
    egal
    1.48
    ologia
    1.44
    pora
    1.40
    emic
    1.37
    ocur
    1.34
    ovation
    1.34
    clamation
    1.33
    Activations Density 4.898%

    No Known Activations