© 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. 1-RES-SM
    11. 23824
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate existence or presence

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.29
    1.7%
    427
    +0.11
    0.7%
    12
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.29
    0.09
    485
    +0.11
    0.04
    418
    +0.10
    0.02
    Negative Logits
    .*;
    -1.77
    =”
    -1.77
    ’,
    -1.72
    erated
    -1.69
    ’.
    -1.69
    .’
    -1.52
    uar
    -1.49
    ressor
    -1.45
    ”,
    -1.44
    ifies
    -1.41
    POSITIVE LOGITS
    Ļª
    2.23
    ·¸
    2.01
    Īĺ
    1.96
    ĻĤ
    1.96
    ľĵ
    1.91
    ´
    1.90
    ¥
    1.81
    ħ
    1.75
    ²
    1.75
    ĥ½
    1.70
    Activations Density 1.010%

    No Known Activations