© 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. 1-RES-SM
    11. 24792
    Prev
    Next
    INDEX
    Explanations

    terms related to magnetism and magnetic properties

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.18
    1.0%
    2
    +0.13
    0.7%
    129
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.18
    0.01
    304
    +0.13
    0.01
    508
    +0.12
    0.01
    Negative Logits
     possible
    -1.86
     complete
    -1.81
     recommend
    -1.67
     culmin
    -1.57
     reasoned
    -1.54
    orems
    -1.52
     adopt
    -1.52
     practical
    -1.51
     choosing
    -1.50
     forthcoming
    -1.49
    POSITIVE LOGITS
    finger
    1.97
    illas
    1.80
    rup
    1.74
    Ĵ
    1.70
    romagnetic
    1.64
    bean
    1.63
    ĨĴ
    1.63
    well
    1.61
    ĻĤ
    1.59
    lens
    1.58
    Activations Density 0.023%

    No Known Activations