© 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. 24069
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to liability and court cases

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    111
    +0.18
    1.0%
    271
    +0.16
    0.9%
    71
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.18
    0.03
    157
    +0.16
    0.02
    271
    +0.14
    0.00
    Negative Logits
    olithic
    -1.71
     Norton
    -1.62
     adolescence
    -1.58
     nowhere
    -1.47
    jections
    -1.42
     epoch
    -1.39
     adulthood
    -1.38
     Bonferroni
    -1.37
     epochs
    -1.36
     corresponded
    -1.29
    POSITIVE LOGITS
    ERTY
    1.65
    icles
    1.58
    nis
    1.53
    lop
    1.52
    rag
    1.45
    nell
    1.44
    EMENT
    1.43
    icle
    1.41
    lov
    1.37
     COURT
    1.36
    Activations Density 0.054%

    No Known Activations