© 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. 31362
    Prev
    Next
    INDEX
    Explanations

    references to various types of weapons, particularly knives and swords

    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
    +0.16
    0.9%
    169
    +0.13
    0.8%
    94
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.16
    -0.01
    148
    +0.13
    0.00
    173
    +0.12
    0.03
    Negative Logits
    UGH
    -1.84
     booked
    -1.77
    uran
    -1.68
    ergic
    -1.50
    frast
    -1.49
    ities
    -1.49
     circumstances
    -1.49
     APPEALS
    -1.48
    OMA
    -1.48
     suppose
    -1.48
    POSITIVE LOGITS
     blades
    2.35
    hammer
    1.97
    chair
    1.92
    bone
    1.90
    stro
    1.89
     blade
    1.89
    backs
    1.87
    wise
    1.81
    smith
    1.79
    bones
    1.78
    Activations Density 0.505%

    No Known Activations