© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24203
    Prev
    Next
    INDEX
    Explanations

    names and references to religious affiliations

    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
    156
    +0.20
    1.2%
    30
    +0.12
    0.7%
    409
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    272
    +0.20
    0.06
    230
    +0.12
    0.07
    101
    +0.11
    0.05
    Negative Logits
     defendant
    -1.80
     unequal
    -1.74
     nothing
    -1.67
     no
    -1.62
     none
    -1.61
     inward
    -1.60
     formalin
    -1.57
     neither
    -1.55
     fewer
    -1.55
     plaintiff
    -1.53
    POSITIVE LOGITS
    clesiast
    1.86
    uary
    1.74
    ertation
    1.61
    igraphy
    1.59
    ÃŃf
    1.57
    ULAR
    1.55
    ipel
    1.55
    )|$(
    1.53
    fessor
    1.52
    Soc
    1.49
    Activations Density 1.384%

    No Known Activations