© 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. 23816
    Prev
    Next
    INDEX
    Explanations

    structured data attributes and configurations

    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
    143
    +0.13
    0.7%
    206
    +0.12
    0.7%
    110
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.13
    0.06
    379
    +0.12
    0.06
    206
    +0.11
    0.05
    Negative Logits
    Ļª
    -4.06
    ¿½
    -4.00
    ľ
    -3.79
    Ĺ
    -3.71
    ľĵ
    -3.66
    ·¸
    -3.63
    ĻĤ
    -3.55
    ¤
    -3.43
    ij
    -3.41
    Īĺ
    -3.40
    POSITIVE LOGITS
    /.
    1.90
    league
    1.67
    ^](#
    1.62
    à«ĩ
    1.61
    thouse
    1.61
    ró
    1.61
    cción
    1.60
    emis
    1.58
    ERY
    1.57
    ruptcy
    1.53
    Activations Density 0.256%

    No Known Activations