© 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. 2-RES-SM
    11. 27054
    Prev
    Next
    INDEX
    Explanations

    information related to significant events or notable figures

    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
    478
    +0.26
    1.5%
    217
    +0.16
    0.9%
    23
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.26
    0.08
    390
    +0.16
    0.04
    383
    +0.16
    0.05
    Negative Logits
    inux
    -1.98
    ERY
    -1.82
    "}](#
    -1.75
    LEY
    -1.73
     expire
    -1.70
    coe
    -1.68
     regimes
    -1.67
    isty
    -1.64
    uelle
    -1.64
    vier
    -1.61
    POSITIVE LOGITS
    _>
    1.62
     forth
    1.46
     Future
    1.43
    iÄĩ
    1.43
     missing
    1.42
    rap
    1.40
     Truth
    1.38
     true
    1.38
     Nothing
    1.34
     truth
    1.34
    Activations Density 0.330%

    No Known Activations