© 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. 4-RES-SM
    11. 13409
    Prev
    Next
    INDEX
    Explanations

    keywords related to "order" and its variations

    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
    437
    +0.13
    0.7%
    307
    +0.12
    0.7%
    104
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.13
    0.03
    104
    +0.12
    0.01
    378
    +0.12
    0.03
    Negative Logits
    kered
    -1.62
    hookrightarrow
    -1.47
    TAIN
    -1.46
    irtual
    -1.45
    stitute
    -1.43
    lı
    -1.41
    fiddle
    -1.41
    LLOW
    -1.39
    UTERS
    -1.39
    ideos
    -1.36
    POSITIVE LOGITS
    »¿
    2.70
    ī
    2.57
    ®
    2.51
    ©
    2.43
    liness
    2.37
    ¢
    2.36
    µ
    2.29
    ģ
    2.27
    «
    2.26
    §
    2.20
    Activations Density 0.313%

    No Known Activations