© 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. 13351
    Prev
    Next
    INDEX
    Explanations

    lines of code or syntax comments

    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
    +0.17
    1.0%
    369
    +0.17
    1.0%
    478
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.17
    0.03
    112
    +0.17
    0.04
    424
    +0.14
    0.03
    Negative Logits
    ese
    -1.56
    matics
    -1.53
     stake
    -1.50
    Äį
    -1.50
    ath
    -1.41
    uries
    -1.40
    inary
    -1.40
    ilty
    -1.38
     estate
    -1.35
    ots
    -1.35
    POSITIVE LOGITS
    Į
    3.03
    ¿½
    2.95
    ĥ½
    2.93
    Ĵ
    2.87
    ↵
    2.87
       ↵
    2.87
    2.87
    <|outofrange|>
    2.87
    ↵
    2.87
    2.87
    Activations Density 0.110%

    No Known Activations