© 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. 4-RES-SM
    11. 9706
    Prev
    Next
    INDEX
    Explanations

    a mixture of emotional expressions and their corresponding levels

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.35
    2.2%
    397
    +0.12
    0.8%
    53
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.35
    0.03
    255
    +0.12
    0.00
    450
    +0.11
    0.01
    Negative Logits
    ,^[@
    -1.74
     centered
    -1.62
    .^[@
    -1.57
     favor
    -1.53
     canceled
    -1.45
     ([**
    -1.44
     [(\[
    -1.40
     utilized
    -1.40
     included
    -1.40
     sequenced
    -1.37
    POSITIVE LOGITS
    Category
    3.45
    IJ
    1.68
    monton
    1.60
    »
    1.59
    Ļ
    1.57
    Ĵ
    1.56
    ĥ½
    1.51
    #:
    1.50
    |-
    1.44
    ¬
    1.44
    Activations Density 0.044%

    No Known Activations