© 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 EvalsExportsAPI 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. 27957
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sp"

    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
    369
    +0.19
    1.1%
    65
    +0.11
    0.6%
    371
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.19
    0.02
    65
    +0.11
    0.02
    349
    +0.11
    0.02
    Negative Logits
    ľĵ
    -2.76
    ĥ
    -2.68
    ¼
    -2.61
    ¥
    -2.53
    ĵ
    -2.51
    ¾
    -2.51
    ħ
    -2.51
    £
    -2.50
    ĸ´
    -2.49
    ĩ
    -2.48
    POSITIVE LOGITS
    ionage
    1.85
    letons
    1.75
    inners
    1.74
    iders
    1.67
    itzer
    1.61
     (@
    1.59
    reader
    1.58
    rock
    1.56
    olars
    1.56
    herical
    1.56
    Activations Density 0.041%

    No Known Activations