© 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. 2-RES-SM
    11. 31440
    Prev
    Next
    INDEX
    Explanations

    mentions of churches and related religious terms

    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
    156
    +0.20
    1.1%
    276
    +0.10
    0.6%
    118
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.20
    0.02
    242
    +0.10
    0.02
    56
    +0.10
    -0.00
    Negative Logits
    <|outofrange|>
    -2.59
    ↵
    -2.59
    ↵
    -2.59
    ↵↵
    -2.59
     ↵
    -2.59
    -2.59
     ↵
    -2.59
    č↵
    -2.59
             ↵
    -2.59
    ↵
    -2.59
    POSITIVE LOGITS
    yard
    2.62
    yards
    2.06
    holder
    1.89
    member
    1.84
    holders
    1.80
    master
    1.77
     hierarchy
    1.74
    iller
    1.68
    istory
    1.63
    arm
    1.59
    Activations Density 0.140%

    No Known Activations