© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 28084
    Prev
    Next
    INDEX
    Explanations

    keywords related to delivery services and logistics

    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
    141
    +0.16
    0.9%
    176
    +0.15
    0.8%
    31
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.16
    0.10
    176
    +0.15
    0.15
    123
    +0.12
    0.14
    Negative Logits
    stown
    -1.42
    οÏħÏĤ
    -1.41
    bard
    -1.40
     perpendicular
    -1.34
    's
    -1.31
    +.
    -1.28
    cht
    -1.26
     bones
    -1.26
     logo
    -1.25
    gel
    -1.25
    POSITIVE LOGITS
    olation
    1.86
    ults
    1.74
    izations
    1.70
    urbs
    1.68
    ocations
    1.58
    ressions
    1.55
    ership
    1.51
    itions
    1.50
    izers
    1.48
    ![**
    1.48
    Activations Density 4.925%

    No Known Activations