© 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. 13563
    Prev
    Next
    INDEX
    Explanations

    instances of violent crime and incidents involving firearms

    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
    56
    +0.14
    0.8%
    179
    +0.14
    0.8%
    243
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.14
    -0.04
    179
    +0.14
    0.09
    54
    +0.10
    0.10
    Negative Logits
    imum
    -1.97
    oracle
    -1.91
    doms
    -1.84
     favor
    -1.82
    idity
    -1.81
     richer
    -1.80
     generation
    -1.71
    theorem
    -1.68
    idem
    -1.68
    .*,
    -1.67
    POSITIVE LOGITS
     police
    2.75
    Police
    2.42
     Police
    2.38
     handc
    2.37
     parked
    2.35
     footage
    2.31
     arrests
    2.30
     suspects
    2.29
     videot
    2.23
     injuries
    2.17
    Activations Density 4.798%

    No Known Activations