© 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. 26669
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court cases and procedural matters

    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
    +0.22
    1.3%
    369
    +0.14
    0.8%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.22
    0.12
    54
    +0.14
    0.11
    10
    +0.12
    0.07
    Negative Logits
    ensity
    -1.75
    inction
    -1.50
    ixed
    -1.47
    yet
    -1.47
    stood
    -1.45
    rimination
    -1.43
    rectomy
    -1.41
    standing
    -1.38
     inheritance
    -1.38
    reek
    -1.37
    POSITIVE LOGITS
     interested
    2.20
     reporters
    1.94
     person
    1.84
     professionals
    1.76
     reporter
    1.76
     producers
    1.74
     parties
    1.72
     talented
    1.71
     partners
    1.69
     experts
    1.68
    Activations Density 2.656%

    No Known Activations