© 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. 23932
    Prev
    Next
    INDEX
    Explanations

    structured data formats

    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
    369
    +0.15
    0.8%
    81
    +0.14
    0.8%
    274
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.15
    0.10
    458
    +0.14
    0.07
    203
    +0.12
    0.08
    Negative Logits
    worth
    -1.58
    ous
    -1.56
    acies
    -1.55
    roph
    -1.52
    »¿
    -1.48
    otrophic
    -1.45
    ously
    -1.44
    pires
    -1.42
     Revolution
    -1.38
    holders
    -1.37
    POSITIVE LOGITS
    255
    1.76
    sek
    1.62
    000000
    1.59
    dern
    1.55
    px
    1.54
    rf
    1.52
    eno
    1.52
    0000
    1.50
    nd
    1.47
    256
    1.47
    Activations Density 0.540%

    No Known Activations