© 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. 12408
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and their values

    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
    220
    +0.11
    0.6%
    478
    +0.11
    0.6%
    432
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.11
    0.03
    432
    +0.11
    0.03
    220
    +0.11
    0.03
    Negative Logits
    ritten
    -1.61
    operated
    -1.35
    ()</
    -1.34
    erville
    -1.28
     toll
    -1.28
     challenge
    -1.27
    ^[@
    -1.26
    upon
    -1.25
    ?**
    -1.24
    omb
    -1.23
    POSITIVE LOGITS
    NavBar
    1.60
     ole
    1.57
    tsd
    1.56
    ning
    1.52
    px
    1.50
    ns
    1.47
    cember
    1.46
    ľ
    1.45
    bound
    1.45
    °
    1.44
    Activations Density 0.074%

    No Known Activations