© 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. 32198
    Prev
    Next
    INDEX
    Explanations

    technical terms and variables related to coding or software functionalities

    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
    24
    +0.14
    0.8%
    5
    +0.12
    0.7%
    294
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.14
    -0.00
    5
    +0.12
    0.10
    170
    +0.11
    0.09
    Negative Logits
     Edison
    -1.58
     NaCl
    -1.58
    escence
    -1.50
     Einstein
    -1.48
     relativity
    -1.45
    ulations
    -1.45
    yme
    -1.43
    ricanes
    -1.41
    =\"
    -1.38
     clim
    -1.38
    POSITIVE LOGITS
     itself
    1.79
     closely
    1.55
    alion
    1.50
    dagger
    1.48
    ounder
    1.44
    rely
    1.42
     Its
    1.40
     finally
    1.38
     its
    1.36
     exactly
    1.36
    Activations Density 4.401%

    No Known Activations