© 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. 13725
    Prev
    Next
    INDEX
    Explanations

    references to weather phenomena, particularly rain and storms

    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
    430
    +0.14
    0.8%
    392
    +0.13
    0.7%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.14
    0.04
    410
    +0.13
    0.06
    271
    +0.13
    -0.02
    Negative Logits
     view
    -1.84
    OOGLE
    -1.71
     fault
    -1.70
     State
    -1.56
     expected
    -1.51
    ederal
    -1.41
    ators
    -1.41
    opic
    -1.39
     preferred
    -1.38
     premises
    -1.35
    POSITIVE LOGITS
    bows
    1.94
    irez
    1.81
    craft
    1.79
    iness
    1.76
    ous
    1.76
    waves
    1.72
    onica
    1.72
    nier
    1.68
    ble
    1.63
    mons
    1.62
    Activations Density 0.873%

    No Known Activations