© 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. 31277
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to court proceedings

    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
    369
    +0.23
    1.3%
    436
    +0.17
    1.0%
    419
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.23
    0.09
    476
    +0.17
    0.11
    369
    +0.15
    0.02
    Negative Logits
    atively
    -1.77
    icals
    -1.57
    º
    -1.47
     forward
    -1.44
     poles
    -1.43
    Ļª
    -1.38
     missing
    -1.37
    ships
    -1.36
    icy
    -1.34
     forwards
    -1.31
    POSITIVE LOGITS
    sburg
    1.72
    wikipedia
    1.68
    fiddle
    1.66
    autres
    1.50
    autre
    1.49
    inian
    1.49
    ')->
    1.45
    ruct
    1.44
    idenote
    1.43
    compile
    1.38
    Activations Density 1.877%

    No Known Activations