© 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. 30949
    Prev
    Next
    INDEX
    Explanations

    references to environmental hazards, particularly related to fire

    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
    335
    +0.14
    0.8%
    410
    +0.13
    0.7%
    189
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.14
    0.02
    410
    +0.13
    0.03
    189
    +0.12
    0.03
    Negative Logits
     age
    -1.60
     kidding
    -1.56
    ¢
    -1.50
    ority
    -1.49
    prise
    -1.48
    prises
    -1.48
     modulus
    -1.46
    velope
    -1.42
     viscosity
    -1.42
     represent
    -1.38
    POSITIVE LOGITS
    ghan
    2.09
    fered
    2.05
    ayette
    1.96
    actory
    1.73
    lic
    1.67
    rost
    1.66
    s
    1.64
    lesh
    1.59
    ortun
    1.58
    erguson
    1.56
    Activations Density 0.205%

    No Known Activations